{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:14:55Z","timestamp":1777407295308,"version":"3.51.4"},"reference-count":296,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"Major Research Plan of the National Natural Science Foundation of China","award":["92370110"],"award-info":[{"award-number":["92370110"]}]},{"DOI":"10.13039\/501100001809","name":"Joint Funds of National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U21B2009"],"award-info":[{"award-number":["U21B2009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>Large Language Models (LLMs) have demonstrated remarkable effectiveness across various domain-specific applications. However, which fundamental capabilities most contribute to their success in different domains remains unclear. This uncertainty complicates LLM evaluation, as existing benchmark-based assessments often fail to capture their real-world performance, where the required capabilities may differ from those measured in the benchmarks. In this survey, we provide a systematic introduction to LLMs\u2019 fundamental capabilities, encompassing their definitions, formation mechanisms, and practical applications. We further explore the relationships among these capabilities and discuss how they collectively support complex problem-solving in domain-specific applications. Building on this foundation, we review recent advances in LLM-driven applications across nine specific domains: medicine, law, computational biology, finance, social sciences and psychology, computer programming and software engineering, robots and agents, AI for disciplines, and creative work. We analyze how specific capabilities are leveraged for each domain to address unique requirements. This perspective enables us to establish connections between these capabilities and domain requirements, and to evaluate the varying importance of different capabilities across different domains. Based on these insights, we propose evaluation strategies tailored to the essential capabilities required in each domain, offering practical guidance for selecting suitable backbone LLMs in real-world applications.<\/jats:p>","DOI":"10.1145\/3735632","type":"journal-article","created":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T07:09:36Z","timestamp":1747292976000},"page":"1-42","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Fundamental Capabilities and Applications of Large Language Models: A Survey"],"prefix":"10.1145","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8784-1330","authenticated-orcid":false,"given":"Jiawei","family":"Li","sequence":"first","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2422-0548","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8319-5805","authenticated-orcid":false,"given":"Yizhe","family":"Yang","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2036-0789","authenticated-orcid":false,"given":"Yu","family":"Bai","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1053-5375","authenticated-orcid":false,"given":"Xiaofeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9439-8544","authenticated-orcid":false,"given":"Yinghao","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1317-5251","authenticated-orcid":false,"given":"Huashan","family":"Sun","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9558-7611","authenticated-orcid":false,"given":"Yuhang","family":"Liu","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4499-4347","authenticated-orcid":false,"given":"Xingpeng","family":"Si","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9842-9314","authenticated-orcid":false,"given":"Yuhao","family":"Ye","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9840-4372","authenticated-orcid":false,"given":"Yixiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7837-2317","authenticated-orcid":false,"given":"Yiguan","family":"Lin","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6021-1119","authenticated-orcid":false,"given":"Bin","family":"Xu","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8622-9937","authenticated-orcid":false,"given":"Bowen","family":"Ren","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1691-1584","authenticated-orcid":false,"given":"Chong","family":"Feng","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0320-7520","authenticated-orcid":false,"given":"Heyan","family":"Huang","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Beijing Institute of Technology","place":["Beijing, China"]}]}],"member":"320","published-online":{"date-parts":[[2025,9,8]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx431"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.2196\/48291"},{"key":"e_1_3_2_4_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Aher Gati V.","year":"2023","unstructured":"Gati V. Aher, Rosa I. Arriaga, and Adam Tauman Kalai. 2023. Using large language models to simulate multiple humans and replicate human subject studies. In Proceedings of the International Conference on Machine Learning. PMLR, 337\u2013371. https:\/\/proceedings.mlr.press\/v202\/aher23a.html"},{"key":"e_1_3_2_5_2","unstructured":"Brian Ichter Anthony Brohan Yevgen Chebotar Chelsea Finn Karol Hausman Alexander Herzog Daniel Ho Julian Ibarz Alex Irpan Eric Jang et\u00a0al. 2022. Do as I can not as I say: Grounding language in robotic affordances. In Conference on Robot Learning CoRL 2022 14-18 December 2022 Auckland New Zealand (Proceedings of Machine Learning Research Vol. 205). PMLR 287\u2013318. https:\/\/proceedings.mlr.press\/v205\/ichter23a.html"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Elif Akata Lion Schulz Julian Coda-Forno Seong Joon Oh Matthias Bethge and Eric Schulz. 2023. Playing repeated games with large language models. (2023). arXiv:2305.16867. DOI:10.48550\/ARXIV.2305.16867","DOI":"10.48550\/ARXIV.2305.16867"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Badr AlKhamissi Millicent Li Asli Celikyilmaz Mona T. Diab and Marjan Ghazvininejad. 2022. A review on language models as knowledge bases. (2022). arXiv:2204.06031. DOI:10.48550\/ARXIV.2204.06031","DOI":"10.48550\/ARXIV.2204.06031"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Emily Alsentzer John R. Murphy Willie Boag Wei-Hung Weng Di Jin Tristan Naumann and Matthew B. A. McDermott. 2019. Publicly available clinical BERT embeddings. arXiv:1904.03323. DOI:10.48550\/arXiv.1904.03323","DOI":"10.48550\/arXiv.1904.03323"},{"key":"e_1_3_2_9_2","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","year":"2022","unstructured":"Cem Anil, Yuhuai Wu, Anders Andreassen, Aitor Lewkowycz, Vedant Misra, Vinay V. Ramasesh, Ambrose Slone, Guy Gur-Ari, Ethan Dyer, and Behnam Neyshabur. 2022. Exploring length generalization in large language models. In Proceedings of the International Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_10_2","unstructured":"Jacob Austin Augustus Odena Maxwell I. Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie J. Cai Michael Terry Quoc V. Le and Charles Sutton. 2021. Program synthesis with large language models. (2021). arXiv:2108.07732."},{"key":"e_1_3_2_11_2","unstructured":"Pranjal Awasthi and Anupam Gupta. 2023. Improving length-generalization in transformers via task hinting. arxiv:2310.00726 [cs.LG]. Retrieved from https:\/\/arxiv.org\/abs\/2310.00726"},{"key":"e_1_3_2_12_2","volume-title":"Baichuan-13b","year":"2023","unstructured":"Baichuan-inc. 2023. Baichuan-13b. Retrieved May 25, 2025 from https:\/\/github.com\/baichuan-inc\/Baichuan-13B"},{"key":"e_1_3_2_13_2","volume-title":"Proceedings of the AIED 2023","author":"Bainbridge Katie","year":"2023","unstructured":"Katie Bainbridge, Candace A. Walkington, Armon Ibrahim, Iris Zhong, Debshila Basu Mallick, Julianna Washington, and Richard G. Baraniuk. 2023. A case study using large language models to generate metadata for math questions. In Proceedings of the AIED 2023."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAB354"},{"key":"e_1_3_2_15_2","volume-title":"Proceedings of the of COLING","author":"Bertolini Lorenzo","year":"2022","unstructured":"Lorenzo Bertolini, Julie Weeds, and David Weir. 2022. Testing large language models on compositionality and inference with phrase-level adjective-noun entailment. In Proceedings of the of COLING."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21496"},{"key":"e_1_3_2_17_2","unstructured":"Satwik Bhattamishra Arkil Patel Phil Blunsom and Varun Kanade. 2024. Understanding in-context learning in transformers and LLMs by learning to learn discrete functions. In The Twelfth International Conference on Learning Representations ICLR 2024 Vienna Austria May 7-11 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=ekeyCgeRfC"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3587431"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Kaifeng Bi Lingxi Xie Hengheng Zhang Xin Chen Xiaotao Gu and Qi Tian. 2022. Pangu-Weather: A 3D high-resolution model for fast and accurate global weather forecast. (2022). arXiv:2211.02556. DOI:10.48550\/ARXIV.2211.02556","DOI":"10.48550\/ARXIV.2211.02556"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06185-3"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Andrew Blair-Stanek Nils Holzenberger and Benjamin Van Durme. 2023. Can GPT-3 perform statutory reasoning? In Proceedings of the Nineteenth International Conference on Artificial Intelligence and Law ICAIL 2023 Braga Portugal June 19-23 2023. ACM 22\u201331. DOI:10.1145\/3594536.3595163","DOI":"10.1145\/3594536.3595163"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Michael J. Bommarito II and Daniel Martin Katz. 2022. GPT takes the bar exam. (2022). arXiv:2212.14402. DOI:10.48550\/ARXIV.2212.14402","DOI":"10.48550\/ARXIV.2212.14402"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Andres M. Bran Sam Cox Oliver Schilter Carlo Baldassari Andrew D. White and Philippe Schwaller. 2024. Augmenting large language models with chemistry tools. Nat. Mac. Intell. 6 5 (2024) 525\u2013535. DOI:10.1038\/S42256-024-00832-8","DOI":"10.1038\/S42256-024-00832-8"},{"key":"e_1_3_2_24_2","volume-title":"Proceedings of the 12th International Conference on Computational Creativity","author":"Branch Boyd","year":"2021","unstructured":"Boyd Branch, Piotr Mirowski, and Kory W. Mathewson. 2021. Collaborative storytelling with human actors and AI narrators. In Proceedings of the 12th International Conference on Computational Creativity."},{"key":"e_1_3_2_25_2","article-title":"Language models are few-shot learners","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, et\u00a0al. 2020. Language models are few-shot learners. Proceedings of the NeurIPS.","journal-title":"Proceedings of the NeurIPS"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-022-03036-1"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Tuhin Chakrabarty Philippe Laban Divyansh Agarwal Smaranda Muresan and Chien-Sheng Wu. 2024. Art or artifice? Large language models and the false promise of creativity. In Proceedings of the CHI Conference on Human Factors in Computing Systems CHI 2024 Honolulu HI USA May 11-16 2024. ACM 30:1\u201330:34. DOI:10.1145\/3613904.3642731","DOI":"10.1145\/3613904.3642731"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.460"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Ilias Chalkidis Manos Fergadiotis Prodromos Malakasiotis Nikolaos Aletras and Ion Androutsopoulos. 2020. LEGAL-BERT: The muppets straight out of law school. arXiv:2010.02559.","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"e_1_3_2_30_2","unstructured":"Chi-Min Chan Weize Chen Yusheng Su Jianxuan Yu Wei Xue Shanghang Zhang Jie Fu and Zhiyuan Liu. 2024. ChatEval: Towards better LLM-based evaluators through multi-agent debate. In The Twelfth International Conference on Learning Representations ICLR 2024 Vienna Austria May 7-11 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=FQepisCUWu"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Bo Chen Xingyi Cheng Pan Li Yangli-ao Geng Jing Gong Shen Li Zhilei Bei Xu Tan Boyan Wang Xin Zeng et\u00a0al. 2024. xTrimoPGLM: Unified 100B-Scale pre-trained transformer for deciphering the language of protein. (2024). arXiv:2401.06199. DOI:10.48550\/ARXIV.2401.06199","DOI":"10.48550\/ARXIV.2401.06199"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad221"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Jin Chen Zheng Liu Xu Huang Chenwang Wu Qi Liu Gangwei Jiang Yuanhao Pu Yuxuan Lei Xiaolong Chen Xingmei Wang et\u00a0al. 2024. When large language models meet personalization: Perspectives of challenges and opportunities. World Wide Web (WWW) 27 4 (2024) 42. DOI:10.1007\/S11280-024-01276-1","DOI":"10.1007\/S11280-024-01276-1"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Jiaao Chen Xiaoman Pan Dian Yu Kaiqiang Song Xiaoyang Wang Dong Yu and Jianshu Chen. 2023. Skills-in-context prompting: Unlocking compositionality in large language models. (2023). arXiv:2308.00304. DOI:10.48550\/ARXIV.2308.00304","DOI":"10.48550\/ARXIV.2308.00304"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Kang Chen Tao Han Junchao Gong Lei Bai Fenghua Ling Jing-Jia Luo Xi Chen Leiming Ma Tianning Zhang Rui Su et\u00a0al. 2023. FengWu: Pushing the skillful global medium-range weather forecast beyond 10 Days Lead. (2023). arXiv:2304.02948. DOI:10.48550\/ARXIV.2304.02948","DOI":"10.48550\/ARXIV.2304.02948"},{"key":"e_1_3_2_36_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Pond\u00e9 de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et\u00a0al. 2021. Evaluating large language models trained on code. (2021). arXiv:2107.03374."},{"key":"e_1_3_2_37_2","unstructured":"Wenhu Chen Xueguang Ma Xinyi Wang and William W. Cohen. 2023. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. Trans. Mach. Learn. Res. 2023 (2023). https:\/\/openreview.net\/forum?id=YfZ4ZPt8zd"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Weize Chen Yusheng Su Jingwei Zuo Cheng Yang Chenfei Yuan Chen Qian Chi-Min Chan Yujia Qin Yaxi Lu Ruobing Xie et\u00a0al. 2023. AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv:2308.10848. DOI:10.48550\/ARXIV.2308.10848","DOI":"10.48550\/ARXIV.2308.10848"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Yirong Chen Zhenyu Wang Xiaofen Xing Huimin Zheng Zhipei Xu Kai Fang Junhong Wang Sihang Li Jieling Wu Qi Liu and Xiangmin Xu. 2023. BianQue: Balancing the questioning and suggestion ability of health LLMs with multi-turn health conversations polished by ChatGPT. arXiv:2310.15896. DOI:10.48550\/ARXIV.2310.15896","DOI":"10.48550\/ARXIV.2310.15896"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Zheng Chen. 2023. PALR: Personalization aware LLMs for recommendation. arXiv:2305.07622. DOI:10.48550\/ARXIV.2305.07622","DOI":"10.48550\/ARXIV.2305.07622"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Zeming Chen Alejandro Hern\u00e1ndez-Cano Angelika Romanou Antoine Bonnet Kyle Matoba Francesco Salvi Matteo Pagliardini Simin Fan Andreas K\u00f6pf Amirkeivan Mohtashami et\u00a0al. 2023. MEDITRON-70B: scaling medical pretraining for large language models. (2023). arXiv:2311.16079. DOI:10.48550\/ARXIV.2311.16079","DOI":"10.48550\/ARXIV.2311.16079"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_43_2","unstructured":"Jonathan H. Choi Kristin E. Hickman Amy B. Monahan and Daniel Schwarcz. 2021. ChatGPT goes to law school. J. Legal Educ. 71 (2021) 387."},{"key":"e_1_3_2_44_2","volume-title":"Proceedings of the Summit on Clinical Research Informatics, CRI 2016","author":"Choi Youngduck","year":"2016","unstructured":"Youngduck Choi, Chill Yi-I Chiu, and David A. Sontag. 2016. Learning low-dimensional representations of medical concepts. In Proceedings of the Summit on Clinical Research Informatics, CRI 2016."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","unstructured":"Ratul Chowdhury Nazim Bouatta Surojit Biswas Christina Floristean Anant Kharkar Koushik Roy Charlotte Rochereau Gustaf Ahdritz Joanna Zhang George M. Church et\u00a0al. 2022. Single-sequence protein structure prediction using a language model and deep learning. Nature Biotechnology 40 11 (2022) 1617\u20131623. DOI:10.1038\/s41587-022-01432-w","DOI":"10.1038\/s41587-022-01432-w"},{"key":"e_1_3_2_46_2","article-title":"UniProt: The universal protein knowledgebase in 2023","author":"Consortium The UniProt","year":"2022","unstructured":"The UniProt Consortium. 2022. UniProt: The universal protein knowledgebase in 2023. Nucleic Acids Research (2022).","journal-title":"Nucleic Acids Research"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Jiaxi Cui Zongjian Li Yang Yan Bohua Chen and Li Yuan. 2023. Chatlaw: Open-source legal large language model with integrated external knowledge bases. arXiv:2306.16092. DOI:10.48550\/ARXIV.2306.16092","DOI":"10.48550\/ARXIV.2306.16092"},{"key":"e_1_3_2_48_2","unstructured":"Wenliang Dai Junnan Li Dongxu Li Anthony Meng Huat Tiong Junqi Zhao Weisheng Wang Boyang Li Pascale Fung and Steven C. H. Hoi. 2023. InstructBLIP: Towards general-purpose vision-language models with instruction tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10-16 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/9a6a435e75419a836fe47ab6793623e6-Abstract-Conference.html"},{"key":"e_1_3_2_49_2","article-title":"The art in the artificial AI and the creative industries","author":"Davies J.","year":"2020","unstructured":"J. Davies, J. Klinger, J. Mateos-Garcia, and K. Stathoulopoulos. 2020. The art in the artificial AI and the creative industries. Creat Ind Policy Evid Centre (2020).","journal-title":"Creat Ind Policy Evid Centre"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/2701413"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Yinlin Deng Chunqiu Steven Xia Chenyuan Yang Shizhuo Dylan Zhang Shujing Yang and Lingming Zhang. 2023. Large language models are edge-case fuzzers: Testing deep learning libraries via FuzzGPT. arXiv:2304.02014. DOI:10.48550\/ARXIV.2304.02014","DOI":"10.48550\/ARXIV.2304.02014"},{"key":"e_1_3_2_52_2","unstructured":"Aniket Deroy Kripabandhu Ghosh and Saptarshi Ghosh. 2023. How ready are pre-trained abstractive models and LLMs for legal case judgement summarization?. In Proceedings of the Third International Workshop on Artificial Intelligence and Intelligent Assistance for Legal Professionals in the Digital Workplace (LegalAIIA 2023) co-located with the 19th International Conference on Artificial Intelligence and Law (ICAIL 2023) Braga Portugal June 19 2023 (CEUR Workshop Proceedings Vol. 3423). CEUR-WS.org 8\u201319. https:\/\/ceurws.org\/Vol-3423\/paper2.pdf"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","unstructured":"Jingzhe Ding Yan Cen and Xinyuan Wei. 2023. Using large language model to solve and explain physics word problems approaching human level. arXiv:2309.08182. DOI:10.48550\/ARXIV.2309.08182","DOI":"10.48550\/ARXIV.2309.08182"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","unstructured":"Yihong Dong Xue Jiang Zhi Jin and Ge Li. 2024. Self-collaboration code generation via ChatGPT. ACM Trans. Softw. Eng. Methodol. 33 7 (2024) 189:1\u2013189:38. DOI:10.1145\/3672459","DOI":"10.1145\/3672459"},{"key":"e_1_3_2_55_2","unstructured":"Danny Driess Fei Xia Mehdi S. M. Sajjadi Corey Lynch Aakanksha Chowdhery Brian Ichter Ayzaan Wahid Jonathan Tompson Quan Vuong Tianhe Yu et\u00a0al. 2023. PaLM-E: An embodied multimodal language model. In International Conference on Machine Learning ICML 2023 23-29 July 2023 Honolulu Hawaii USA (Proceedings of Machine Learning Research Vol. 202). PMLR 8469\u20138488. https:\/\/proceedings.mlr.press\/v202\/driess23a.html"},{"key":"e_1_3_2_56_2","unstructured":"Yilun Du Shuang Li Antonio Torralba Joshua B. Tenenbaum and Igor Mordatch. 2024. Improving factuality and reasoning in language models through multiagent debate. In Forty-first International Conference on Machine Learning ICML 2024 Vienna Austria July 21-27 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=zj7YuTE4t8"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","unstructured":"Shaoxiong Duan and Yining Shi. 2023. From interpolation to extrapolation: Complete length generalization for arithmetic transformers. arXiv:2310.11984. DOI:10.48550\/ARXIV.2310.11984","DOI":"10.48550\/ARXIV.2310.11984"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","unstructured":"Naoki Egami Musashi Jacobs-Harukawa Brandon M. Stewart and Hanying Wei. 2023. Using large language model annotations for valid downstream statistical inference in social science: Design-based semi-supervised learning. arXiv:2306.04746. DOI:10.48550\/ARXIV.2306.04746","DOI":"10.48550\/ARXIV.2306.04746"},{"key":"e_1_3_2_59_2","doi-asserted-by":"crossref","unstructured":"Ahmed Elnaggar Michael Heinzinger Christian Dallago Ghalia Rehawi Yu Wang Llion Jones Tom Gibbs Tamas Feher Christoph Angerer Martin Steinegger et\u00a0al. 2020. ProtTrans: Towards cracking the language of life\u2019s code through self-supervised deep learning and high performance computing. (2020). arXiv:2007.06225.","DOI":"10.1101\/2020.07.12.199554"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","unstructured":"Zachary Englhardt Richard Li Dilini Nissanka Zhihan Zhang Girish Narayanswamy Joseph Breda Xin Liu Shwetak N. Patel and Vikram Iyer. 2023. Exploring and characterizing large language models for embedded system development and debugging. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems CHI EA 2024 Honolulu HI USA May 11-16 2024. ACM 150:1\u2013150:9. DOI:10.1145\/3613905.3650764","DOI":"10.1145\/3613905.3650764"},{"key":"e_1_3_2_61_2","unstructured":"Linxi Fan Guanzhi Wang Yunfan Jiang Ajay Mandlekar Yuncong Yang Haoyi Zhu Andrew Tang De-An Huang Yuke Zhu and Anima Anandkumar. 2022. MineDojo: Building open-ended embodied agents with internet-scale knowledge. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 NeurIPS 2022 New Orleans LA USA November 28 - December 9 2022. http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/74a67268c5cc5910f64938cac4526a90-Abstract-Datasets_and_Benchmarks.html"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","unstructured":"Xiaomin Fang Fan Wang Lihang Liu Jingzhou He Dayong Lin Yingfei Xiang Xiaonan Zhang Hua Wu Hui Li and Le Song. 2022. HelixFold-Single: MSA-free protein structure prediction by using protein language model as an alternative. arXiv:2207.13921. DOI:10.48550\/ARXIV.2207.13921","DOI":"10.48550\/ARXIV.2207.13921"},{"key":"e_1_3_2_63_2","unstructured":"Weixi Feng Wanrong Zhu Tsu-Jui Fu Varun Jampani Arjun R. Akula Xuehai He Sugato Basu Xin Eric Wang and William Yang Wang. 2023. LayoutGPT: Compositional visual planning and generation with large language models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10-16 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/3a7f9e485845dac27423375c934cb4db-Abstract-Conference.html"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","unstructured":"Lorenzo Jaime Yu Flores Heyuan Huang Kejian Shi Sophie Chheang and Arman Cohan. 2023. Medical text simplification: Optimizing for readability with unlikelihood training and reranked beam search decoding. In Findings of the Association for Computational Linguistics: EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 4859\u20134873. DOI:10.18653\/V1\/2023.FINDINGS-EMNLP.322","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.322"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","unstructured":"Giorgio Franceschelli and Mirco Musolesi. 2023. On the creativity of large language models. arXiv:2304.00008. DOI:10.48550\/ARXIV.2304.00008","DOI":"10.48550\/ARXIV.2304.00008"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","unstructured":"Guanghui Fu Qing Zhao Jianqiang Li Dan Luo Changwei Song Wei Zhai Shuo Liu Fan Wang Yan Wang Lijuan Cheng et\u00a0al. 2023. Enhancing psychological counseling with large language model: A multifaceted decision-support system for non-professionals. arXiv:2308.15192. DOI:10.48550\/ARXIV.2308.15192","DOI":"10.48550\/ARXIV.2308.15192"},{"key":"e_1_3_2_67_2","article-title":"Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning","author":"Gainza Pablo","year":"2019","unstructured":"Pablo Gainza, Freyr Sverrisson, F. Monti, Emanuele Rodol\u00e0, D. Boscaini, Michael M. Bronstein, and Bruno E. Correia. 2019. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nature Methods (2019).","journal-title":"Nature Methods"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","unstructured":"Chen Gao Xiaochong Lan Zhihong Lu Jinzhu Mao Jinghua Piao Huandong Wang Depeng Jin and Yong Li. 2023. S \\({}^{\\mbox{3}}\\) : Social-network simulation system with large language model-empowered agents. arXiv:2307.14984. DOI:10.48550\/ARXIV.2307.14984","DOI":"10.48550\/ARXIV.2307.14984"},{"key":"e_1_3_2_69_2","article-title":"DESTINI: A deep-learning approach to contact-driven protein structure prediction","author":"Gao Mu","year":"2019","unstructured":"Mu Gao, Hongyi Zhou, and Jeffrey Skolnick. 2019. DESTINI: A deep-learning approach to contact-driven protein structure prediction. Scientific Reports (2019).","journal-title":"Scientific Reports"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/URTC56832.2022.10002218"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","unstructured":"Vedant Gaur and Nikunj Saunshi. 2023. Reasoning in large language models through symbolic math word problems. In Findings of the Association for Computational Linguistics: ACL 2023 Toronto Canada July 9-14 2023. Association for Computational Linguistics 5889\u20135903. DOI:10.18653\/V1\/2023.FINDINGS-ACL.364","DOI":"10.18653\/V1\/2023.FINDINGS-ACL.364"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","unstructured":"Mingyang Geng Shangwen Wang Dezun Dong Haotian Wang Ge Li Zhi Jin Xiaoguang Mao and Xiangke Liao. 2024. Large language models are few-shot summarizers: Multi-intent comment generation via in-context learning. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering ICSE 2024 Lisbon Portugal April 14-20 2024. ACM 39:1\u201339:13. DOI:10.1145\/3597503.3608134","DOI":"10.1145\/3597503.3608134"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","unstructured":"Vladimir Gligorijevi\u0107 P. Douglas Renfrew Tomasz Kosci\u00f3lek Julia Koehler Leman Daniel Berenberg Tommi Vatanen Chris Chandler Bryn C. Taylor Ian Fisk Hera Vlamakis et\u00a0al. 2021. Structure-based protein function prediction using graph convolutional networks. Nature Communications 12 1 (2021) 3168. DOI:10.1038\/s41467-021-23303-9","DOI":"10.1038\/s41467-021-23303-9"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","unstructured":"Tomas Goldsack Zhihao Zhang Chen Tang Carolina Scarton and Chenghua Lin. 2023. Enhancing biomedical lay summarisation with external knowledge graphs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 8016\u20138032. DOI:10.18653\/V1\/2023.EMNLP-MAIN.498","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.498"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","unstructured":"Lewis D. Griffin Bennett Kleinberg Maximilian Mozes Kimberly T. Mai Maria Vau Matthew Caldwell and Augustine Marvor-Parker. 2023. Susceptibility to influence of large language models. arXiv:2303.06074. DOI:10.48550\/ARXIV.2303.06074","DOI":"10.48550\/ARXIV.2303.06074"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.499"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Y. Wu Y. K. Li et al.2024. DeepSeek-Coder: When the large language model meets programming - the rise of code intelligence. arXiv:2401.14196. DOI:10.48550\/ARXIV.2401.14196","DOI":"10.48550\/ARXIV.2401.14196"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.58"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","unstructured":"Zishan Guo Renren Jin Chuang Liu Yufei Huang Dan Shi Supryadi Linhao Yu Yan Liu Jiaxuan Li Bojian Xiong and Deyi Xiong. 2023. Evaluating large language models: A comprehensive survey. arXiv:2310.19736. DOI:10.48550\/ARXIV.2310.19736","DOI":"10.48550\/ARXIV.2310.19736"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","unstructured":"Suchin Gururangan Ana Marasovic Swabha Swayamdipta Kyle Lo Iz Beltagy Doug Downey and Noah A. Smith. 2020. Don\u2019t stop pretraining: Adapt language models to domains and tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics Online 8342\u20138360. DOI:10.18653\/v1\/2020.acl-main.740","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_3_2_81_2","article-title":"REALM: Retrieval-augmented language model pre-training","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Z. Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. REALM: Retrieval-augmented language model pre-training. Proceedings of the International Conference on Machine Learning.","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","unstructured":"Thilo Hagendorff Sarah Fabi and Michal Kosinski. 2022. Machine intuition: Uncovering human-like intuitive decision-making in GPT-3.5. arXiv:2212.05206. DOI:10.48550\/ARXIV.2212.05206","DOI":"10.48550\/ARXIV.2212.05206"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","unstructured":"Sil Hamilton. 2023. Blind judgement: Agent-based supreme court modelling with GPT. arXiv:2301.05327. DOI:10.48550\/ARXIV.2301.05327","DOI":"10.48550\/ARXIV.2301.05327"},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","unstructured":"Chi Han Qifan Wang Wenhan Xiong Yu Chen Heng Ji and Sinong Wang. 2023. LM-Infinite: Simple on-the-fly length generalization for large language models. arXiv:2308.16137. DOI:10.48550\/ARXIV.2308.16137","DOI":"10.48550\/ARXIV.2308.16137"},{"key":"e_1_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1177\/01410768231181251"},{"key":"e_1_3_2_86_2","doi-asserted-by":"publisher","unstructured":"Joy He-Yueya Gabriel Poesia Rose E. Wang and Noah D. Goodman. 2023. Solving math word problems by combining language models with symbolic solvers. arXiv:2304.09102. DOI:10.48550\/ARXIV.2304.09102","DOI":"10.48550\/ARXIV.2304.09102"},{"key":"e_1_3_2_87_2","unstructured":"Sirui Hong Xiawu Zheng Jonathan Chen Yuheng Cheng Jinlin Wang Ceyao Zhang Zili Wang Steven Ka Shing Yau Zijuan Lin Liyang Zhou et al.2023. MetaGPT: Meta programming for multi-agent collaborative framework. In The Twelfth International Conference on Learning Representations ICLR 2024 Vienna Austria May 7-11 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=VtmBAGCN7o"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","unstructured":"Bozhen Hu Jun-Xiong Xia Jiangbin Zheng Cheng Tan Yufei Huang Yongjie Xu and Stan Z. Li. 2022. Protein language models and structure prediction: Connection and progression. arXiv:2211.16742. DOI:10.48550\/ARXIV.2211.16742","DOI":"10.48550\/ARXIV.2211.16742"},{"key":"e_1_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"e_1_3_2_90_2","unstructured":"Quzhe Huang Mingxu Tao Zhenwei An Chen Zhang Cong Jiang Zhibin Chen Zirui Wu and Yansong Feng. 2023. Lawyer LLaMA technical report. arXiv:2305.15062. Retrieved from https:\/\/arxiv.org\/abs\/2305.15062"},{"key":"e_1_3_2_91_2","unstructured":"Wenlong Huang Fei Xia Ted Xiao Harris Chan Jacky Liang Pete Florence Andy Zeng Jonathan Tompson Igor Mordatch Yevgen Chebotar et\u00a0al. 2022. Inner monologue: Embodied reasoning through planning with language models. In Conference on Robot Learning CoRL 2022 14-18 December 2022 Auckland New Zealand (Proceedings of Machine Learning Research Vol. 205). PMLR 1769\u20131782. https:\/\/proceedings.mlr.press\/v205\/huang23c.html"},{"key":"e_1_3_2_92_2","doi-asserted-by":"publisher","unstructured":"Atin Sakkeer Hussain Shansong Liu Chenshuo Sun and Ying Shan. 2023. M \\({}^{\\mbox{2}}\\) UGen: Multi-modal music understanding and generation with the power of large language models. arXiv:2311.11255. DOI:10.48550\/ARXIV.2311.11255","DOI":"10.48550\/ARXIV.2311.11255"},{"key":"e_1_3_2_93_2","unstructured":"Kwan Yuen Iu and Vanessa Man-Yi Wong. 2023. ChatGPT by OpenAI: The end of litigation lawyers? Retrieved May 25 2025 from https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4339839"},{"key":"e_1_3_2_94_2","doi-asserted-by":"publisher","unstructured":"Kevin Maik Jablonka Qianxiang Ai Alexander Al-Feghali Shruti Badhwar Joshua D. Bocarsly Andres M. Bran Stefan Bringuier et\u00a0al. 2023. 14 examples of how LLMs can transform materials science and chemistry: A reflection on a large language model Hackathon. arXiv:2306.06283. DOI:10.48550\/ARXIV.2306.06283","DOI":"10.48550\/ARXIV.2306.06283"},{"key":"e_1_3_2_95_2","unstructured":"Samy Jelassi St\u00e9phane d\u2019Ascoli Carles Domingo-Enrich Yuhuai Wu Yuanzhi Li and Fran\u00e7ois Charton. 2023. Length generalization in arithmetic transformers. arxiv:2306.15400 [cs.LG] Retrieved from https:\/\/arxiv.org\/abs\/2306.15400"},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","unstructured":"Zhenlan Ji Pingchuan Ma Zongjie Li and Shuai Wang. 2023. Benchmarking and explaining large language model-based code generation: A causality-centric approach. arXiv:2310.06680. DOI:10.48550\/ARXIV.2310.06680","DOI":"10.48550\/ARXIV.2310.06680"},{"key":"e_1_3_2_97_2","doi-asserted-by":"publisher","unstructured":"Jinhao Jiang Kun Zhou Zican Dong Keming Ye Xin Zhao and Ji-RongWen. 2023. StructGPT: A general framework for large language model to reason over structured data. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 9237\u20139251. DOI:10.18653\/V1\/2023.EMNLP-MAIN.574","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.574"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","unstructured":"Shuyang Jiang Yuhao Wang and Yu Wang. 2023. SelfEvolve: A code evolution framework via large language models. arXiv:2306.02907. DOI:10.48550\/ARXIV.2306.02907","DOI":"10.48550\/ARXIV.2306.02907"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.3390\/app11146421"},{"key":"e_1_3_2_100_2","doi-asserted-by":"publisher","unstructured":"Qiao Jin Bhuwan Dhingra Zhengping Liu William W. Cohen and Xinghua Lu. 2019. PubMedQA: A dataset for biomedical research question answering. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing EMNLP-IJCNLP 2019 Hong Kong China November 3-7 2019. Association for Computational Linguistics 2567\u20132577. DOI:10.18653\/V1\/D19-1259","DOI":"10.18653\/V1\/D19-1259"},{"key":"e_1_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3357432"},{"key":"e_1_3_2_102_2","article-title":"Retrieval augmented generation of symbolic music with LLMs","author":"Jonason Nicolas","year":"2023","unstructured":"Nicolas Jonason, Luca Casini, Carl Thom\u00e9, et\u00a0al. 2023. Retrieval augmented generation of symbolic music with LLMs. CoRR (2023).","journal-title":"CoRR"},{"key":"e_1_3_2_103_2","doi-asserted-by":"publisher","unstructured":"Sebastian Joseph Kathryn Kazanas Keziah Reina Vishnesh J. Ramanathan Wei Xu Byron C. Wallace and Junyi Jessy Li. 2023. Multilingual simplification of medical texts. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 16662\u201316692. DOI:10.18653\/V1\/2023.EMNLPMAIN.1037","DOI":"10.18653\/V1\/2023.EMNLPMAIN.1037"},{"key":"e_1_3_2_104_2","doi-asserted-by":"publisher","unstructured":"Harshit Joshi Jos\u00e9 Pablo Cambronero S\u00e1nchez Sumit Gulwani Vu Le Gust Verbruggen and Ivan Radicek. 2023. Repair is nearly generation: Multilingual program repair with LLMs. In Thirty-Seventh AAAI Conference on Artificial Intelligence AAAI 2023 Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence IAAI 2023 Thirteenth Symposium on Educational Advances in Artificial Intelligence EAAI 2023 Washington DC USA February 7-14 2023. AAAI Press 5131\u20135140. DOI:10.1609\/AAAI.V37I4.25642","DOI":"10.1609\/AAAI.V37I4.25642"},{"key":"e_1_3_2_105_2","doi-asserted-by":"publisher","unstructured":"John M. Jumper Richard Evans Alexander Pritzel et\u00a0al. 2021. Highly accurate protein structure prediction with AlphaFold. Nature 596 7873 (2021) 583\u2013589. DOI:10.1038\/s41586-021-03819-2","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_106_2","doi-asserted-by":"publisher","unstructured":"Jean Kaddour Joshua Harris Maximilian Mozes Herbie Bradley Roberta Raileanu and Robert McHardy. 2023. Challenges and applications of large language models. arXiv:2307.10169. DOI:10.48550\/ARXIV.2307.10169","DOI":"10.48550\/ARXIV.2307.10169"},{"key":"e_1_3_2_107_2","doi-asserted-by":"publisher","unstructured":"Wang-Cheng Kang Jianmo Ni Nikhil Mehta Maheswaran Sathiamoorthy Lichan Hong Ed H. Chi and Derek Zhiyuan Cheng. 2023. Do LLMs understand user preferences? Evaluating LLMs on user rating prediction. arXiv:2305.06474. DOI:10.48550\/ARXIV.2305.06474","DOI":"10.48550\/ARXIV.2305.06474"},{"key":"e_1_3_2_108_2","doi-asserted-by":"publisher","unstructured":"Ehud Karpas Omri Abend Yonatan Belinkov Barak Lenz Opher Lieber Nir Ratner et\u00a0al. 2022. MRKL systems: A modular neuro-symbolic architecture that combines large language models external knowledge sources and discrete reasoning. arXiv:2205.00445. DOI:10.48550\/ARXIV.2205.00445","DOI":"10.48550\/ARXIV.2205.00445"},{"key":"e_1_3_2_109_2","doi-asserted-by":"crossref","unstructured":"Daniel Martin Katz Michael James Bommarito Shang Gao and Pablo Arredondo. 2024. Gpt-4 passes the bar exam. Philosophical Transactions of the Royal Society A 382 2270 (2024) 20230254.","DOI":"10.1098\/rsta.2023.0254"},{"key":"e_1_3_2_110_2","unstructured":"Tushar Khot H. Trivedi Matthew Finlayson Yao Fu Kyle Richardson Peter Clark and Ashish Sabharwal. 2023. Decomposed prompting: A modular approach for solving complex tasks. https:\/\/openreview.net\/forum?id=_nGgzQjzaRy"},{"key":"e_1_3_2_111_2","unstructured":"Takeshi Kojima Shixiang Shane Gu Machel Reid Yutaka Matsuo and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 NeurIPS 2022 New Orleans LA USA November 28 - December 9 2022. http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/8bb0d291acd4acf06ef112099c16f326-Abstract-Conference.html"},{"key":"e_1_3_2_112_2","doi-asserted-by":"publisher","unstructured":"Michal Kosinski. 2023. Theory of mind may have spontaneously emerged in large language models. arXiv:2302.02083. DOI:10.48550\/ARXIV.2302.02083","DOI":"10.48550\/ARXIV.2302.02083"},{"key":"e_1_3_2_113_2","doi-asserted-by":"publisher","unstructured":"Tiffany H. Kung Morgan Cheatham Arielle Medenilla Czarina Sillos Lorie De Leon Camille Elepa\u00f1o Maria Madriaga Rimel Aggabao Giezel Diaz-Candido James Maningo and Victor Tseng. 2023. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digital Health 2 2 (2023) 1\u201312. DOI:10.1371\/journal.pdig.0000198","DOI":"10.1371\/journal.pdig.0000198"},{"key":"e_1_3_2_114_2","doi-asserted-by":"publisher","unstructured":"Tin Lai Yukun Shi Zicong Du Jiajie Wu Ken Fu Yichao Dou and Ziqi Wang. 2023. Psy-LLM: Scaling up global mental health psychological services with AI-based large language models. arXiv:2307.11991. DOI:10.48550\/ARXIV.2307.11991","DOI":"10.48550\/ARXIV.2307.11991"},{"key":"e_1_3_2_115_2","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-023-06668-3"},{"key":"e_1_3_2_116_2","article-title":"Can LLMs be good financial advisors?: An initial study in personal decision making for optimized outcomes","author":"Lakkaraju Kausik","year":"2023","unstructured":"Kausik Lakkaraju, Sai Krishna Revanth Vuruma, Vishal Pallagani, and Bharath Muppasani. 2023. Can LLMs be good financial advisors?: An initial study in personal decision making for optimized outcomes. CoRR (2023).","journal-title":"CoRR"},{"key":"e_1_3_2_117_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V39I17.33989"},{"key":"e_1_3_2_118_2","unstructured":"Cheng Li Ziang Leng Chenxi Yan Junyi Shen Hao Wang Weishi MI Yaying Fei et\u00a0al. 2023. ChatHaruhi: Reviving anime character in reality via large language model. arXiv:2308.09597. Retrieved from https:\/\/arxiv.org\/abs\/2308.09597"},{"key":"e_1_3_2_119_2","unstructured":"Chunyuan Li Cliff Wong Sheng Zhang Naoto Usuyama Haotian Liu Jianwei Yang Tristan Naumann Hoifung Poon and Jianfeng Gao. 2023. LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10-16 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/5abcdf8ecdcacba028c6662789194572-Abstract-Datasets_and_Benchmarks.html"},{"key":"e_1_3_2_120_2","unstructured":"Guohao Li Hasan Abed Al Kader Hammoud Hani Itani Dmitrii Khizbullin and Bernard Ghanem. 2023. Camel: Communicative agents for \u201cmind\u201d exploration of large scale language model society. arXiv:2303.17760. Retrieved from https:\/\/arxiv.org\/abs\/2303.17760"},{"key":"e_1_3_2_121_2","doi-asserted-by":"publisher","unstructured":"Hang Li. 2022. Language models: Past present and future. Commun. ACM 65 7 (2022) 56\u201363. DOI:10.1145\/3490443","DOI":"10.1145\/3490443"},{"key":"e_1_3_2_122_2","doi-asserted-by":"publisher","unstructured":"Haonan Li Yu Hao Yizhuo Zhai and Zhiyun Qian. 2023. The hitchhiker\u2019s guide to program analysis: A journey with large language models. arXiv:2308.00245. DOI:10.48550\/ARXIV.2308.00245","DOI":"10.48550\/ARXIV.2308.00245"},{"key":"e_1_3_2_123_2","doi-asserted-by":"publisher","unstructured":"Jia Li Ge Li Yongmin Li and Zhi Jin. 2023. Structured chain-of-thought prompting for code generation. ACM Trans. Softw. Eng. Methodol. 34 2 (2025) 37:1\u201337:23. DOI:10.1145\/3690635","DOI":"10.1145\/3690635"},{"key":"e_1_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.599"},{"key":"e_1_3_2_125_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580488"},{"key":"e_1_3_2_126_2","article-title":"Symbolic chain-of-thought distillation: Small models can also \u201cThink\u201d step-by-step","author":"Li Liunian Harold","year":"2023","unstructured":"Liunian Harold Li, Jack Hessel, Youngjae Yu, Xiang Ren, Kai-Wei Chang, and Yejin Choi. 2023. Symbolic chain-of-thought distillation: Small models can also \u201cThink\u201d step-by-step. In Proceedings of the Annual Meeting of the Association for Computational Linguistics.","journal-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics"},{"key":"e_1_3_2_127_2","doi-asserted-by":"publisher","unstructured":"Qi Li. 2023. Harnessing the power of pre-trained vision-language models for efficient medical report generation. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management CIKM 2023 Birmingham United Kingdom October 21-25 2023. ACM 1308\u20131317. DOI:10.1145\/3583780.3614961","DOI":"10.1145\/3583780.3614961"},{"key":"e_1_3_2_128_2","doi-asserted-by":"publisher","unstructured":"Siyu Li Jin Yang and Kui Zhao. 2023. Are you in a Masquerade? Exploring the behavior and impact of large language model driven social bots in online social networks. arXiv:2307.10337. DOI:10.48550\/ARXIV.2307.10337","DOI":"10.48550\/ARXIV.2307.10337"},{"key":"e_1_3_2_129_2","doi-asserted-by":"publisher","unstructured":"Xianzhi Li Samuel Chan Xiaodan Zhu Yulong Pei Zhiqiang Ma Xiaomo Liu and Sameena Shah. 2023. Are ChatGPT and GPT-4 general-purpose solvers for financial text analytics? A study on several typical tasks. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: EMNLP 2023 - Industry Track Singapore December 6-10 2023. Association for Computational Linguistics 408\u2013422. DOI:10.18653\/V1\/2023.EMNLP-INDUSTRY.39","DOI":"10.18653\/V1\/2023.EMNLP-INDUSTRY.39"},{"key":"e_1_3_2_130_2","doi-asserted-by":"publisher","unstructured":"Xin-Ye Li Jiang-Tian Xue Zheng Xie and Ming Li. 2023. Think outside the code: Brainstorming boosts large language models in code generation. arXiv:2305.10679. DOI:10.48550\/ARXIV.2305.10679","DOI":"10.48550\/ARXIV.2305.10679"},{"key":"e_1_3_2_131_2","doi-asserted-by":"publisher","unstructured":"Xiang Lorraine Li Adhiguna Kuncoro Jordan Hoffmann Cyprien de Masson d\u2019Autume Phil Blunsom and Aida Nematzadeh. 2022. A systematic investigation of commonsense knowledge in large language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing EMNLP 2022 Abu Dhabi United Arab Emirates December 7-11 2022. Association for Computational Linguistics 11838\u201311855. DOI:10.18653\/V1\/2022.EMNLP-MAIN.812","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.812"},{"key":"e_1_3_2_132_2","doi-asserted-by":"publisher","unstructured":"Yunxiang Li Zihan Li Kai Zhang Ruilong Dan and You Zhang. 2023. ChatDoctor: A medical chat model fine-tuned on LLaMA model using medical domain knowledge. arXiv:2303.14070. DOI:10.48550\/ARXIV.2303.14070","DOI":"10.48550\/ARXIV.2303.14070"},{"key":"e_1_3_2_133_2","doi-asserted-by":"publisher","unstructured":"Yuan Li Yixuan Zhang and Lichao Sun. 2023. MetaAgents: Simulating interactions of human behaviors for LLM-based task-oriented coordination via collaborative generative agents. arXiv:2310.06500. DOI:10.48550\/ARXIV.2310.06500","DOI":"10.48550\/ARXIV.2310.06500"},{"key":"e_1_3_2_134_2","unstructured":"Long Lian Boyi Li Adam Yala and Trevor Darrell. 2024. LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models. Trans. Mach. Learn. Res. 2024 (2024). https:\/\/openreview.net\/forum?id=hFALpTb4fR"},{"key":"e_1_3_2_135_2","doi-asserted-by":"crossref","unstructured":"Tian Liang Zhiwei He Wenxiang Jiao Xing Wang Yan Wang Rui Wang Yujiu Yang Zhaopeng Tu and Shuming Shi. 2023. Encouraging divergent thinking in large language models through multi-agent debate. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing EMNLP 2024 Miami FL USA November 12-16 2024. Association for Computational Linguistics 17889\u201317904. https:\/\/aclanthology.org\/2024.emnlp-main.992","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"e_1_3_2_136_2","doi-asserted-by":"publisher","unstructured":"Zhiding Liang Jinglei Cheng Rui Yang Hang Ren Zhixin Song Di Wu Xuehai Qian Tongyang Li and Yiyu Shi. 2023. Unleashing the potential of LLMs for quantum computing: A study in quantum architecture design. (2023). arXiv:2307.08191. DOI:10.48550\/ARXIV.2307.08191","DOI":"10.48550\/ARXIV.2307.08191"},{"key":"e_1_3_2_137_2","doi-asserted-by":"publisher","unstructured":"Valentin Li\u00e9vin Christoffer Egeberg Hother and Ole Winther. 2024. Can large language models reason about medical questions?Patterns 5 3 (2024) 100943. DOI:10.1016\/J.PATTER.2024.100943","DOI":"10.1016\/J.PATTER.2024.100943"},{"key":"e_1_3_2_138_2","unstructured":"Valentin Li\u00e9vin Andreas Geert Motzfeldt Ida Riis Jensen and Ole Winther. 2023. Variational open-domain question answering. In International Conference on Machine Learning ICML 2023 23-29 July 2023 Honolulu Hawaii USA (Proceedings of Machine Learning Research Vol. 202). PMLR 20950\u201320977. https:\/\/proceedings.mlr.press\/v202\/lievin23a.html"},{"key":"e_1_3_2_139_2","doi-asserted-by":"publisher","unstructured":"Jonathan Light Wei Cheng Yue Wu Masafumi Oyamada Mengdi Wang Santiago Paternain and Haifeng Chen. 2025. DISC: Dynamic decomposition improves LLM inference scaling. arXiv:2502.16706. DOI:10.48550\/ARXIV.2502.16706","DOI":"10.48550\/ARXIV.2502.16706"},{"key":"e_1_3_2_140_2","unstructured":"Jonathan Light Yue Wu Yiyou Sun Wenchao Yu Yanchi Liu Xujiang Zhao Ziniu Hu Haifeng Chen and Wei Cheng. 2025. SFS: Smarter code space search improves LLM inference scaling. In The Thirteenth International Conference on Learning Representations ICLR 2025 Singapore April 24-28 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=MCHuGOkExF"},{"key":"e_1_3_2_141_2","doi-asserted-by":"publisher","unstructured":"Jiaju Lin Haoran Zhao Aochi Zhang Yiting Wu Huqiuyue Ping and Qin Chen. 2023. AgentSims: An open-source sandbox for large language model evaluation. arXiv:2308.04026. DOI:10.48550\/ARXIV.2308.04026","DOI":"10.48550\/ARXIV.2308.04026"},{"key":"e_1_3_2_142_2","doi-asserted-by":"publisher","unstructured":"Zeming Lin Halil Akin Roshan Rao Brian L. Hie Zhongkai Zhu Wenting Lu Nikita Smetanin Robert Verkuil Ori Kabeli Yaniv Shmueli et al.2023. Evolutionary-scale prediction of atomic level protein structure with a language model. Science 379 6637 (2023) 1123\u20131130. DOI:10.1126\/science.ade2574","DOI":"10.1126\/science.ade2574"},{"key":"e_1_3_2_143_2","doi-asserted-by":"publisher","unstructured":"Chao Liu Xuanlin Bao Hongyu Zhang Neng Zhang Haibo Hu Xiaohong Zhang and Meng Yan. 2023. Improving ChatGPT prompt for code generation. arXiv:2305.08360. DOI:10.48550\/ARXIV.2305.08360","DOI":"10.48550\/ARXIV.2305.08360"},{"key":"e_1_3_2_144_2","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual instruction tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10-16 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/6dcf277ea32ce3288914faf369fe6de0-Abstract-Conference.html"},{"key":"e_1_3_2_145_2","doi-asserted-by":"publisher","unstructured":"June M. Liu Donghao Li He Cao Tianhe Ren Zeyi Liao and Jiamin Wu. 2023. ChatCounselor: A large language models for mental health support. arXiv:2309.15461. DOI:10.48550\/ARXIV.2309.15461","DOI":"10.48550\/ARXIV.2309.15461"},{"key":"e_1_3_2_146_2","doi-asserted-by":"publisher","unstructured":"Xiao-Yang Liu Guoxuan Wang and Daochen Zha. 2023. FinGPT: Democratizing internet-scale data for financial large language models. arXiv:2307.10485. DOI:10.48550\/ARXIV.2307.10485","DOI":"10.48550\/ARXIV.2307.10485"},{"key":"e_1_3_2_147_2","doi-asserted-by":"publisher","unstructured":"Yiren Liu Si Chen Haocong Cheng Mengxia Yu Xiao Ran Andrew Mo Yiliu Tang and Yun Huang. 2024. How AI processing delays foster creativity: Exploring research question co-creation with an LLM-based agent. In Proceedings of the CHI Conference on Human Factors in Computing Systems CHI 2024 Honolulu HI USA May 11-16 2024. ACM 17:1\u201317:25. DOI:10.1145\/3613904.3642698","DOI":"10.1145\/3613904.3642698"},{"key":"e_1_3_2_148_2","doi-asserted-by":"publisher","unstructured":"Zhuang Liu Degen Huang Kaiyu Huang Zhuang Li and Jun Zhao. 2020. FinBERT: A pre-trained financial language representation model for financial text mining. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence IJCAI 2020. ijcai.org 4513\u20134519. DOI:10.24963\/IJCAI.2020\/622","DOI":"10.24963\/IJCAI.2020\/622"},{"key":"e_1_3_2_149_2","doi-asserted-by":"publisher","unstructured":"Anton Lozhkov Raymond Li Loubna Ben Allal Federico Cassano Joel Lamy-Poirier Nouamane Tazi Ao Tang Dmytro Pykhtar Jiawei Liu Yuxiang Wei et\u00a0al. 2024. StarCoder 2 and The Stack v2: The Next Generation. (2024). arXiv:2402.19173. DOI:10.48550\/ARXIV.2402.19173","DOI":"10.48550\/ARXIV.2402.19173"},{"key":"e_1_3_2_150_2","doi-asserted-by":"publisher","unstructured":"Junru Lu Jiazheng Li Byron C. Wallace Yulan He and Gabriele Pergola. 2023. NapSS: Paragraph-level medical text simplification via narrative prompting and sentence-matching summarization. In Findings of the Association for Computational Linguistics: EACL 2023 Dubrovnik Croatia May 2-6 2023. Association for Computational Linguistics 1049\u20131061. DOI:10.18653\/V1\/2023.FINDINGS-EACL.80","DOI":"10.18653\/V1\/2023.FINDINGS-EACL.80"},{"key":"e_1_3_2_151_2","unstructured":"Pan Lu Baolin Peng Hao Cheng Michel Galley Kai-Wei Chang Ying Nian Wu Song-Chun Zhu and Jianfeng Gao. 2023. Chameleon: Plug-and-play compositional reasoning with large language models. In Advances in Neural Information Processing Systems 36:Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10-16 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/871ed095b734818cfba48db6aeb25a62-Abstract-Conference.html"},{"key":"e_1_3_2_152_2","doi-asserted-by":"publisher","unstructured":"Renqian Luo Liai Sun Yingce Xia Tao Qin Sheng Zhang Hoifung Poon and Tie-Yan Liu. 2022. BioGPT: Generative pre-trained transformer for biomedical text generation and mining. Briefings in Bioinformatics 23 6 (2022) bbac409. DOI:10.1093\/bib\/bbac409","DOI":"10.1093\/bib\/bbac409"},{"key":"e_1_3_2_153_2","doi-asserted-by":"publisher","unstructured":"Yun Luo Xiaotian Lin Zhen Yang Fandong Meng Jie Zhou and Yue Zhang. 2023. Mitigating catastrophic forgetting in task-incremental continual learning with adaptive classification criterion. (2023). arXiv:2305.12270. DOI:10.48550\/ARXIV.2305.12270","DOI":"10.48550\/ARXIV.2305.12270"},{"key":"e_1_3_2_154_2","doi-asserted-by":"publisher","unstructured":"Yun Luo Zhen Yang Xuefeng Bai Fandong Meng Jie Zhou and Yue Zhang. 2023. Investigating forgetting in pre-trained representations through continual learning. arXiv:2305.05968. DOI:10.48550\/ARXIV.2305.05968","DOI":"10.48550\/ARXIV.2305.05968"},{"key":"e_1_3_2_155_2","doi-asserted-by":"publisher","unstructured":"Yizhen Luo Jiahuan Zhang Siqi Fan Kai Yang Yushuai Wu Mu Qiao and Zaiqing Nie. 2023. BioMedGPT: Open multimodal generative pre-trained transformer for BioMedicine. arXiv:2308.09442. DOI:10.48550\/ARXIV.2308.09442","DOI":"10.48550\/ARXIV.2308.09442"},{"key":"e_1_3_2_156_2","unstructured":"Ziyang Luo Can Xu Pu Zhao Qingfeng Sun Xiubo Geng Wenxiang Hu Chongyang Tao Jing Ma Qingwei Lin and Daxin Jiang. 2023. WizardCoder: Empowering code large language models with evol-instruct. In The Twelfth International Conference on Learning Representations ICLR 2024 Vienna Austria May 7-11 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=UnUwSIgK5W"},{"key":"e_1_3_2_157_2","doi-asserted-by":"publisher","unstructured":"Minkyung Baek Frank DiMaio Ivan Anishchenko Justas Dauparas Sergey Ovchinnikov Gyu Rie Lee Jue Wang Qian Cong Lisa N. Kinch R. Dustin Schaeffer et\u00a0al. 2021. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373 6557 (2021) 871\u2013876. DOI:10.1126\/science.abj8754","DOI":"10.1126\/science.abj8754"},{"key":"e_1_3_2_158_2","doi-asserted-by":"publisher","unstructured":"Teli Ma Rong Li and Junwei Liang. 2024. An examination of the compositionality of large generative vision-language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) NAACL 2024 Mexico City Mexico June 16-21 2024. Association for Computational Linguistics 692\u2013705. DOI:10.18653\/V1\/2024.NAACL-LONG.39","DOI":"10.18653\/V1\/2024.NAACL-LONG.39"},{"key":"e_1_3_2_159_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.90"},{"key":"e_1_3_2_160_2","doi-asserted-by":"publisher","unstructured":"Mounica Maddela Megan Ung Jing Xu Andrea Madotto Heather Foran and Y-Lan Boureau. 2023. Training models to generate recognize and reframe unhelpful thoughts. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics Toronto Canada 13641\u201313660. DOI:10.18653\/v1\/2023.acl-long.763","DOI":"10.18653\/v1\/2023.acl-long.763"},{"key":"e_1_3_2_161_2","doi-asserted-by":"publisher","unstructured":"Vaibhav Mavi Abulhair Saparov and Chen Zhao. 2023. Retrieval-augmented chain-of-thought in semi-structured domains. arXiv:2310.14435. DOI:10.48550\/ARXIV.2310.14435","DOI":"10.48550\/ARXIV.2310.14435"},{"key":"e_1_3_2_162_2","article-title":"Incorporating AI tools into medical education: Harnessing the benefits of ChatGPT and Dall-E","author":"Amri Muhammad Miftahul","year":"2023","unstructured":"Muhammad Miftahul Amri and Urfa Khairatun Hisan. 2023. Incorporating AI tools into medical education: Harnessing the benefits of ChatGPT and Dall-E. Journal of Novel Engineering Science and Technology 2, 2 (2023), 34\u201339.","journal-title":"Journal of Novel Engineering Science and Technology"},{"key":"e_1_3_2_163_2","doi-asserted-by":"publisher","unstructured":"Jaina Mistry Sara Chuguransky Lowri Williams Matloob Qureshi Gustavo A. Salazar Erik L. L. Sonnhammer Silvio C. E. Tosatto Lisanna Paladin Shriya Raj Lorna J. Richardson et\u00a0al. 2021. Pfam: The protein families database in 2021. Nucleic Acids Res. 49 Database-Issue (2021) D412\u2013D419. DOI:10.1093\/NAR\/GKAA913","DOI":"10.1093\/NAR\/GKAA913"},{"key":"e_1_3_2_164_2","doi-asserted-by":"publisher","unstructured":"Marius Mosbach Tiago Pimentel Shauli Ravfogel Dietrich Klakow and Yanai Elazar. 2023. Few-shot Fine-tuning vs. In-context Learning: A fair comparison and evaluation. In Findings of the Association for Computational Linguistics: ACL 2023 Toronto Canada July 9-14 2023. Association for Computational Linguistics 12284\u201312314. DOI:10.18653\/V1\/2023.FINDINGS-ACL.779","DOI":"10.18653\/V1\/2023.FINDINGS-ACL.779"},{"key":"e_1_3_2_165_2","unstructured":"Yida Mu Ben P. Wu William Thorne Ambrose Robinson Nikolaos Aletras Carolina Scarton Kalina Bontcheva and Xingyi Song. 2024. Navigating prompt complexity for zero-shot classification: A study of large language models in computational social science. In Proceedings of the 2024 Joint International Conference on Computational Linguistics Language Resources and Evaluation LREC\/COLING 2024 20-25 May 2024 Torino Italy. ELRA and ICCL 12074\u201312086. https:\/\/aclanthology.org\/2024.lrec-main.1055"},{"key":"e_1_3_2_166_2","doi-asserted-by":"publisher","unstructured":"Muhammad U. Nasir Sam Earle Julian Togelius Steven James and Christopher Cleghorn. 2024. LLMatic: Neural architecture search via large language models and quality diversity optimization. In Proceedings of the Genetic and Evolutionary Computation Conference GECCO 2024 Melbourne VIC Australia July 14-18 2024. ACM. DOI:10.1145\/3638529.3654017","DOI":"10.1145\/3638529.3654017"},{"key":"e_1_3_2_167_2","doi-asserted-by":"publisher","unstructured":"Michel Nass Emil Al\u00e9groth and Robert Feldt. 2024. Improving web element localization by using a large language model. Softw. Test. Verification Reliab. 34 7 (2024). DOI:10.1002\/STVR.1893","DOI":"10.1002\/STVR.1893"},{"key":"e_1_3_2_168_2","unstructured":"Nature Education. 2010. Protein Function."},{"key":"e_1_3_2_169_2","article-title":"Law informs code: A legal informatics approach to aligning artificial intelligence with humans","author":"Nay John J.","year":"2022","unstructured":"John J. Nay. 2022. Law informs code: A legal informatics approach to aligning artificial intelligence with humans. Northwestern Journal of Technology and Intellectual Property 20 (2022), 309.","journal-title":"Northwestern Journal of Technology and Intellectual Property"},{"key":"e_1_3_2_170_2","unstructured":"Ha-Thanh Nguyen. 2023. A brief report on LawGPT 1.0: A virtual legal assistant based on GPT-3. arXiv:2302.05729. Retrieved from https:\/\/arxiv.org\/abs\/2302.05729"},{"key":"e_1_3_2_171_2","unstructured":"Tung Nguyen Johannes Brandstetter Ashish Kapoor Jayesh K. Gupta and Aditya Grover. 2023. ClimaX: A foundation model for weather and climate. In International Conference on Machine Learning ICML 2023 23-29 July 2023 Honolulu Hawaii USA (Proceedings of Machine Learning Research Vol. 202). PMLR 25904\u201325938. https:\/\/proceedings.mlr.press\/v202\/nguyen23a.html"},{"key":"e_1_3_2_172_2","unstructured":"Ansong Ni Srini Iyer Dragomir Radev Veselin Stoyanov Wen-Tau Yih Sida I. Wang and Xi Victoria Lin. 2023. LEVER: Learning to verify language-to-code generation with execution. In International Conference on Machine Learning ICML 2023 23-29 July 2023 Honolulu Hawaii USA (Proceedings of Machine Learning Research Vol. 202). PMLR 26106\u201326128. https:\/\/proceedings.mlr.press\/v202\/ni23b.html"},{"key":"e_1_3_2_173_2","volume-title":"Proceedings of the Workshop on Empowering Education with LLMs - the Next-Gen Interface and Content Generation 2023 Co-located with 24th International Conference on Artificial Intelligence in Education (AIED 2023)","author":"Norberg Kole","year":"2023","unstructured":"Kole Norberg, Husni Almoubayyed, Stephen E. Fancsali, Logan De Ley, Kyle Weldon, April Murphy, and Steven Ritter. 2023. Rewriting math word problems with large language models. In Proceedings of the Workshop on Empowering Education with LLMs - the Next-Gen Interface and Content Generation 2023 Co-located with 24th International Conference on Artificial Intelligence in Education (AIED 2023)."},{"key":"e_1_3_2_174_2","unstructured":"Kolby Nottingham Prithviraj Ammanabrolu Alane Suhr Yejin Choi Hannaneh Hajishirzi Sameer Singh and Roy Fox. 2023. Do embodied agents dream of pixelated sheep: Embodied decision making using language guided world modelling. In International Conference on Machine Learning ICML 2023 23-29 July 2023 Honolulu Hawaii USA (Proceedings of Machine Learning Research Vol. 202). PMLR 26311\u201326325. https:\/\/proceedings.mlr.press\/v202\/nottingham23a.html"},{"key":"e_1_3_2_175_2","article-title":"GPT-4 technical report","year":"2023","unstructured":"OpenAI. 2023. GPT-4 technical report. CoRR (2023).","journal-title":"CoRR"},{"key":"e_1_3_2_176_2","doi-asserted-by":"publisher","unstructured":"Carlos Outeiral and Charlotte M. Deane. 2024. Codon language embeddings provide strong signals for protein engineering. Nat. Mac. Intell. 6 2 (2024) 170\u2013179. DOI:10.1038\/S42256-024-00791-0","DOI":"10.1038\/S42256-024-00791-0"},{"key":"e_1_3_2_177_2","unstructured":"Siru Ouyang Zhuosheng Zhang Bing Yan Xuan Liu Jiawei Han and Lianhui Qin. 2023. Structured Chemistry reasoning with large language models. In Forty-first International Conference on Machine Learning ICML 2024 Vienna Austria July 21-27 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=7R3pzxTSlg"},{"key":"e_1_3_2_178_2","volume-title":"Proceedings of the Conference on Health, Inference, and Learning, CHIL 2022","author":"Pal Ankit","year":"2022","unstructured":"Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022. MedMCQA: A large-scale multi-subject multi-choice dataset for medical domain question answering. In Proceedings of the Conference on Health, Inference, and Learning, CHIL 2022."},{"key":"e_1_3_2_179_2","doi-asserted-by":"publisher","unstructured":"Liangming Pan Alon Albalak Xinyi Wang and William Yang Wang. 2023. Logic-LM: Empowering large language models with symbolic solvers for faithful logical reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 3806\u20133824. DOI:10.18653\/V1\/2023.FINDINGS-EMNLP.248","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.248"},{"key":"e_1_3_2_180_2","doi-asserted-by":"publisher","unstructured":"Bhargavi Paranjape Scott M. Lundberg Sameer Singh Hannaneh Hajishirzi Luke Zettlemoyer and Marco T\u00falio Ribeiro. 2023. ART: Automatic multi-step reasoning and tool-use for large language models. arXiv:2303.09014. DOI:10.48550\/ARXIV.2303.09014","DOI":"10.48550\/ARXIV.2303.09014"},{"key":"e_1_3_2_181_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_2_182_2","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545616"},{"key":"e_1_3_2_183_2","unstructured":"Shishir G. Patil Tianjun Zhang Xin Wang and Joseph E. Gonzalez. 2024. Gorilla: Large language model connected with massive APIs. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024 NeurIPS 2024 Vancouver BC Canada December 10-15 2024. http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/e4c61f578ff07830f5c37378dd3ecb0d-Abstract-Conference.html"},{"key":"e_1_3_2_184_2","doi-asserted-by":"publisher","unstructured":"Nelson Perdig\u00e3o Julian Heinrich Christian Stolte Kenneth S. Sabir Michael J. Buckley Bruce Tabor Beth Signal Brian S. Gloss Christopher J. Hammang Burkhard Rost et\u00a0al. 2015. Unexpected features of the dark proteome. Proceedings of the National Academy of Sciences 112 52 (2015) 15898\u201315903. DOI:10.1073\/pnas.1508380112","DOI":"10.1073\/pnas.1508380112"},{"key":"e_1_3_2_185_2","article-title":"Language models as knowledge bases? In","author":"Petroni Fabio","year":"2019","unstructured":"Fabio Petroni, Tim Rockt\u00e4schel, Patrick Lewis, A. Bakhtin, Yuxiang Wu, Alexander H. Miller, and S. Riedel. 2019. Language models as knowledge bases? In Proceedings of the Conference on Empirical Methods in Natural Language Processing.","journal-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing"},{"key":"e_1_3_2_186_2","doi-asserted-by":"crossref","unstructured":"Tammy Pettinato Oltz. 2023. ChatGPT Professor of Law. Retrieved May 25 2025 from https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4347630","DOI":"10.2139\/ssrn.4347630"},{"key":"e_1_3_2_187_2","doi-asserted-by":"publisher","unstructured":"Laura Plein Wendk\u00fbuni C. Ou\u00e9draogo Jacques Klein and Tegawend\u00e9 F. Bissyand\u00e9. 2024. Automatic generation of test cases based on bug reports: A feasibility study with large language models. In Proceedings of the 2024 IEEE\/ACM 46th International Conference on Software Engineering: Companion Proceedings ICSE Companion 2024 Lisbon Portugal April 14-20 2024. ACM 360\u2013361. DOI:10.1145\/3639478.3643119","DOI":"10.1145\/3639478.3643119"},{"key":"e_1_3_2_188_2","doi-asserted-by":"publisher","unstructured":"Archiki Prasad Alexander Koller Mareike Hartmann Peter Clark Ashish Sabharwal Mohit Bansal and Tushar Khot. 2024. ADaPT: As-needed decomposition and planning with language models. In Findings of the Association for Computational Linguistics: NAACL 2024 Mexico City Mexico June 16-21 2024. Association for Computational Linguistics 4226\u20134252. DOI:10.18653\/V1\/2024.FINDINGSNAACL.264","DOI":"10.18653\/V1\/2024.FINDINGSNAACL.264"},{"key":"e_1_3_2_189_2","doi-asserted-by":"publisher","unstructured":"Shuofei Qiao Yixin Ou Ningyu Zhang Xiang Chen Yunzhi Yao Shumin Deng Chuanqi Tan Fei Huang and Huajun Chen. 2023. Reasoning with language model prompting: A survey. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics Toronto Canada 5368\u20135393. DOI:10.18653\/v1\/2023.acllong.294","DOI":"10.18653\/v1\/2023.acllong.294"},{"key":"e_1_3_2_190_2","doi-asserted-by":"publisher","unstructured":"Wei Qin Zetong Chen Lei Wang Yunshi Lan Weijieying Ren and Richang Hong. 2023. Read diagnose and chat: Towards explainable and interactive LLMs-Augmented depression detection in social media. arXiv:2305.05138. DOI:10.18653\/10.48550\/ARXIV.2305.05138","DOI":"10.18653\/10.48550\/ARXIV.2305.05138"},{"key":"e_1_3_2_191_2","doi-asserted-by":"publisher","unstructured":"Predrag Radivojac Zoran Obradovic David Keith Smith Guang Zhu Slobodan Vucetic Celeste J. Brown J. David Lawson and A. Keith Dunker. 2004. Protein flexibility and intrinsic disorder. Protein Sci 13 1 (Jan. 2004) 71\u201380. DOI:10.1110\/ps.03128904","DOI":"10.1110\/ps.03128904"},{"key":"e_1_3_2_192_2","unstructured":"Krishan Rana Jesse Haviland Sourav Garg Jad Abou-Chakra Ian D. Reid and Niko S\u00fcnderhauf. 2023. SayPlan: Grounding large language models using 3D scene graphs for scalable task planning. In Conference on Robot Learning CoRL 2023 6-9 November 2023 Atlanta GA USA (Proceedings of Machine Learning Research Vol. 229). PMLR 23\u201372. https:\/\/proceedings.mlr.press\/v229\/rana23a.html"},{"key":"e_1_3_2_193_2","doi-asserted-by":"publisher","unstructured":"Mucheng Ren Heyan Huang Yuxiang Zhou Qianwen Cao Yuan Bu and Yang Gao. 2022. TCM-SD: A benchmark for probing syndrome differentiation via natural language processing. In Chinese Computational Linguistics - 21st China National Conference CCL 2022 Nanchang China October 14-16 2022 Proceedings (Lecture Notes in Computer Science Vol. 13603). Springer 247\u2013263. DOI:10.1007\/978-3-031-18315-7_16","DOI":"10.1007\/978-3-031-18315-7_16"},{"key":"e_1_3_2_194_2","doi-asserted-by":"publisher","unstructured":"Baptiste Rozi\u00e8re Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Tal Remez J\u00e9r\u00e9my Rapin et\u00a0al. 2023. Code Llama: Open foundation models for code. (2023). arXiv:2308.12950. DOI:10.48550\/ARXIV.2308.12950","DOI":"10.48550\/ARXIV.2308.12950"},{"key":"e_1_3_2_195_2","doi-asserted-by":"publisher","unstructured":"Andre Niyongabo Rubungo Craig Arnold Barry P. Rand and Adji Bousso Dieng. 2023. LLM-Prop: Predicting physical and electronic properties of crystalline solids from their text descriptions. arXiv:2310.14029. DOI:10.48550\/ARXIV.2310.14029","DOI":"10.48550\/ARXIV.2310.14029"},{"key":"e_1_3_2_196_2","doi-asserted-by":"publisher","unstructured":"Alireza Salemi Sheshera Mysore Michael Bendersky and Hamed Zamani. 2024. LaMP: When large language models meet personalization. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ACL 2024 Bangkok Thailand August 11-16 2024. Association for Computational Linguistics 7370\u20137392. DOI:10.18653\/V1\/2024.ACL-LONG.399","DOI":"10.18653\/V1\/2024.ACL-LONG.399"},{"key":"e_1_3_2_197_2","unstructured":"Victor Sanh Albert Webson Colin Raffel Stephen H. Bach Lintang Sutawika Zaid Alyafeai Antoine Chaffin Arnaud Stiegler Arun Raja Manan Dey et\u00a0al. 2022. Multitask prompted training enables zero-shot task generalization. In The Tenth International Conference on Learning Representations ICLR 2022 Virtual Event April 25-29 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=9Vrb9D0WI4"},{"key":"e_1_3_2_198_2","doi-asserted-by":"publisher","unstructured":"Jaromir Savelka Kevin D. Ashley Morgan A. Gray Hannes Westermann and Huihui Xu. 2023. Explaining legal concepts with augmented large language models (GPT-4). arXiv:2306.09525. DOI:10.48550\/ARXIV.2306.09525","DOI":"10.48550\/ARXIV.2306.09525"},{"key":"e_1_3_2_199_2","doi-asserted-by":"publisher","unstructured":"Michael Schauperl and Rajiah Aldrin Denny. 2022. AI-based protein structure prediction in drug discovery: Impacts and challenges. J. Chem. Inf. Model. 62 13 (2022) 3142\u20133156. DOI:10.1021\/ACS.JCIM.2C00026","DOI":"10.1021\/ACS.JCIM.2C00026"},{"key":"e_1_3_2_200_2","doi-asserted-by":"publisher","DOI":"10.1002\/prot.25585"},{"key":"e_1_3_2_201_2","unstructured":"Timo Schick Jane Dwivedi-Yu Roberto Dess\u00ec Roberta Raileanu Maria Lomeli Luke Zettlemoyer Nicola Cancedda and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10-16 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/d842425e4bf79ba039352da0f658a906-Abstract-Conference.html"},{"key":"e_1_3_2_202_2","doi-asserted-by":"publisher","unstructured":"David B. Searls. 2014. A new online computational biology curriculum. PLoS Comput Biol 10 6 (June 2014) e1003662. DOI:10.1371\/journal.pcbi.1003662","DOI":"10.1371\/journal.pcbi.1003662"},{"key":"e_1_3_2_203_2","doi-asserted-by":"publisher","unstructured":"Abigail See Aneesh Pappu Rohun Saxena Akhila Yerukola and Christopher D. Manning. 2019. Do massively pretrained language models make better storytellers?. In Proceedings of the 23rd Conference on Computational Natural Language Learning CoNLL 2019 Hong Kong China November 3-4 2019. Association for Computational Linguistics 843\u2013861. DOI:10.18653\/V1\/K19-1079","DOI":"10.18653\/V1\/K19-1079"},{"key":"e_1_3_2_204_2","doi-asserted-by":"publisher","unstructured":"Andrew W. Senior Richard Evans John Jumper James Kirkpatrick Laurent Sifre Tim Green Chongli Qin Augustin Z\u00eddek Alexander W. R. Nelson Alex Bridgland et\u00a0al. 2020. Improved protein structure prediction using potentials from deep learning. Nat. 577 7792 (2020) 706\u2013710. DOI:10.1038\/S41586-019-1923-7","DOI":"10.1038\/S41586-019-1923-7"},{"key":"e_1_3_2_205_2","doi-asserted-by":"publisher","unstructured":"Chantal Shaib Millicent L. Li Sebastian Joseph Iain James Marshall Junyi Jessy Li and Byron C. Wallace. 2023. Summarizing simplifying and synthesizing medical evidence using GPT-3 (with varying success). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) ACL 2023 Toronto Canada July 9-14 2023. Association for Computational Linguistics 1387\u20131407. DOI:10.18653\/V1\/2023.ACL-SHORT.119","DOI":"10.18653\/V1\/2023.ACL-SHORT.119"},{"key":"e_1_3_2_206_2","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-023-06647-8"},{"key":"e_1_3_2_207_2","unstructured":"Nan Shao Zefan Cai Hanwei Xu Chonghua Liao Yanan Zheng and Zhilin Yang. 2023. Compositional task representations for large language models. In The Eleventh International Conference on Learning Representations ICLR 2023 Kigali Rwanda May 1-5 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=6axIMJA7ME3"},{"key":"e_1_3_2_208_2","doi-asserted-by":"publisher","unstructured":"Zheyan Shen Jiashuo Liu Yue He Xingxuan Zhang Renzhe Xu Han Yu and Peng Cui. 2021. Towards out-of-distribution generalization: A survey. arXiv:2108.13624. DOI:10.48550\/arXiv.2108.13624","DOI":"10.48550\/arXiv.2108.13624"},{"key":"e_1_3_2_209_2","doi-asserted-by":"publisher","unstructured":"Xiaoming Shi Zeming Liu Chuan Wang Haitao Leng Kui Xue Xiaofan Zhang and Shaoting Zhang. 2023. MidMed: Towards mixed-type dialogues for medical consultation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ACL 2023 Toronto Canada July 9-14 2023. Association for Computational Linguistics 8145\u20138157. DOI:10.18653\/V1\/2023.ACL-LONG.453","DOI":"10.18653\/V1\/2023.ACL-LONG.453"},{"key":"e_1_3_2_210_2","doi-asserted-by":"publisher","unstructured":"Karan Singhal Shekoofeh Azizi Tao Tu S. Sara Mahdavi JasonWei HyungWon Chung Nathan Scales Ajay Kumar Tanwani Heather Cole-Lewis Stephen Pfohl et\u00a0al. 2022. Large language models encode clinical knowledge. (2022). arXiv:2212.13138. DOI:10.48550\/ARXIV.2212.13138","DOI":"10.48550\/ARXIV.2212.13138"},{"key":"e_1_3_2_211_2","doi-asserted-by":"publisher","unstructured":"Karan Singhal Tao Tu Juraj Gottweis Rory Sayres Ellery Wulczyn Le Hou Kevin Clark Stephen Pfohl Heather Cole-Lewis Darlene Neal et\u00a0al. 2023. Towards expert-level medical question answering with large language models. (2023). arXiv:2305.09617. DOI:10.48550\/ARXIV.2305.09617","DOI":"10.48550\/ARXIV.2305.09617"},{"key":"e_1_3_2_212_2","doi-asserted-by":"publisher","unstructured":"Ritwik Sinha Zhao Song and Tianyi Zhou. 2023. A mathematical abstraction for balancing the trade-off between creativity and reality in large language models. arXiv:2306.02295. DOI:10.48550\/ARXIV.2306.02295","DOI":"10.48550\/ARXIV.2306.02295"},{"key":"e_1_3_2_213_2","doi-asserted-by":"publisher","unstructured":"Alexey Skrynnik Zoya Volovikova Marc-Alexandre C\u00f4t\u00e9 Anton Voronov Artem Zholus Negar Arabzadeh Shrestha Mohanty Milagro Teruel Ahmed Awadallah Aleksandr Panov et al.2022. Learning to solve voxel building embodied tasks from pixels and natural language instructions. arXiv:2211.00688. DOI:10.48550\/ARXIV.2211.00688","DOI":"10.48550\/ARXIV.2211.00688"},{"key":"e_1_3_2_214_2","doi-asserted-by":"publisher","unstructured":"Yifan Song Weimin Xiong Dawei Zhu Cheng Li Ke Wang Ye Tian and Sujian Li. 2023. RestGPT: Connecting large language models with real-world applications via RESTful APIs. arXiv:2306.06624. DOI:10.48550\/ARXIV.2306.06624","DOI":"10.48550\/ARXIV.2306.06624"},{"key":"e_1_3_2_215_2","doi-asserted-by":"publisher","unstructured":"Evangelia Spiliopoulou Artidoro Pagnoni Yonatan Bisk and Eduard H. Hovy. 2022. EvEntS ReaLM: Event reasoning of entity states via language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing EMNLP 2022 Abu Dhabi United Arab Emirates December 7-11 2022. Association for Computational Linguistics 1982\u20131997. DOI:10.18653\/V1\/2022.EMNLPMAIN.129","DOI":"10.18653\/V1\/2022.EMNLPMAIN.129"},{"key":"e_1_3_2_216_2","doi-asserted-by":"publisher","unstructured":"Martin Steinegger Milot Mirdita and Johannes S\u00f6ding. 2019. Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold. Nature Methods 16 7 (2019) 603\u2013606. DOI:10.1038\/s41592-019-0437-4","DOI":"10.1038\/s41592-019-0437-4"},{"key":"e_1_3_2_217_2","unstructured":"Douglas Summers-Stay Clare R. Voss and Stephanie M. Lukin. 2023. Brainstorm then Select: A generative language model improves its creativity score. In The AAAI-23 Workshop on Creative AI Across Modalities."},{"key":"e_1_3_2_218_2","unstructured":"Yue Huang Lichao Sun Haoran Wang Siyuan Wu Qihui Zhang Yuan Li Chujie Gao Yixin Huang Wenhan Lyu Yixuan Zhang et\u00a0al. 2024. Position: TrustLLM: Trustworthiness in large language models. In Forty-first International Conference on Machine Learning ICML 2024 Vienna Austria July 21-27 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=bWUU0LwwMp"},{"key":"e_1_3_2_219_2","doi-asserted-by":"publisher","unstructured":"Freyr Sverrisson Jean Feydy Bruno E. Correia and Michael M. Bronstein. 2021. Fast end-to-end learning on protein surfaces. In IEEE Conference on Computer Vision and Pattern Recognition CVPR 2021 virtual June 19-25 2021. Computer Vision Foundation\/IEEE 15272\u201315281. DOI:10.1109\/CVPR46437.2021.01502","DOI":"10.1109\/CVPR46437.2021.01502"},{"key":"e_1_3_2_220_2","doi-asserted-by":"publisher","unstructured":"Ben Swanson Kory Mathewson Ben Pietrzak Sherol Chen and Monica Dinalescu. 2021. Story centaur: Large language model few shot learning as a creative writing tool. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations EACL 2021 Online April 19-23 2021. Association for Computational Linguistics 244\u2013256. DOI:10.18653\/V1\/2021.EACL-DEMOS.29","DOI":"10.18653\/V1\/2021.EACL-DEMOS.29"},{"key":"e_1_3_2_221_2","doi-asserted-by":"publisher","unstructured":"Bowen Tan Zichao Yang Maruan Al-Shedivat Eric P. Xing and Zhiting Hu. 2021. Progressive generation of long text with pretrained language models. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies NAACL-HLT 2021 Online June 6-11 2021. Association for Computational Linguistics 4313\u20134324. DOI:10.18653\/V1\/2021.NAACL-MAIN.341","DOI":"10.18653\/V1\/2021.NAACL-MAIN.341"},{"key":"e_1_3_2_222_2","doi-asserted-by":"publisher","unstructured":"Chen Tang Shun Wang Tomas Goldsack and Chenghua Lin. 2023. Improving biomedical abstractive summarisation with knowledge aggregation from citation papers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 606\u2013618. DOI:10.18653\/V1\/2023.EMNLP-MAIN.40","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.40"},{"key":"e_1_3_2_223_2","doi-asserted-by":"publisher","unstructured":"Jiabin Tang Yuhao Yang Wei Wei Lei Shi Lixin Su Suqi Cheng Dawei Yin and Chao Huang. 2023. GraphGPT: Graph instruction tuning for large language models. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval SIGIR 2024 Washington DC USA July 14-18 2024. ACM 491\u2013500. DOI:10.1145\/3626772.3657775","DOI":"10.1145\/3626772.3657775"},{"key":"e_1_3_2_224_2","volume-title":"Xwin-LM","author":"Team Xwin-LM","year":"2023","unstructured":"Xwin-LM Team. 2023. Xwin-LM. Retrieved May 25, 2025 from https:\/\/github.com\/Xwin-LM\/Xwin-LM"},{"key":"e_1_3_2_225_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"e_1_3_2_226_2","doi-asserted-by":"publisher","unstructured":"Yuanhe Tian Ruyi Gan Yan Song Jiaxing Zhang and Yongdong Zhang. 2024. ChiMed-GPT: A Chinese medical large language model with full training regime and better alignment to human preferences. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ACL 2024 Bangkok Thailand August 11-16 2024. Association for Computational Linguistics 7156\u20137173. DOI:10.18653\/V1\/2024.ACL-LONG.386","DOI":"10.18653\/V1\/2024.ACL-LONG.386"},{"key":"e_1_3_2_227_2","unstructured":"Kushal Tirumala Aram H. Markosyan Luke Zettlemoyer and Armen Aghajanyan. 2022. Memorization without overfitting: Analyzing the training dynamics of large language models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 NeurIPS 2022 New Orleans LA USA November 28 - December 9 2022. http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/fa0509f4dab6807e2cb465715bf2d249-Abstract-Conference.html"},{"key":"e_1_3_2_228_2","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e0re Naman Goyal Eric Hambro Faisal Azhar et al.2023. LLaMA: Open and efficient foundation language models. arXiv:2302.13971. DOI:10.48550\/ARXIV.2302.13971","DOI":"10.48550\/ARXIV.2302.13971"},{"key":"e_1_3_2_229_2","doi-asserted-by":"publisher","unstructured":"Dietrich Trautmann Alina Petrova and Frank Schilder. 2022. Legal prompt engineering for multilingual legal judgement prediction. arXiv:2212.02199. DOI:10.48550\/ARXIV.2212.02199","DOI":"10.48550\/ARXIV.2212.02199"},{"key":"e_1_3_2_230_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1574-6526(07)03024-6"},{"key":"e_1_3_2_231_2","doi-asserted-by":"publisher","unstructured":"Dave Van Veen Cara Van Uden Louis Blankemeier Jean-Benoit Delbrouck Asad Aali Christian Bluethgen Anuj Pareek Malgorzata Polacin William Collins et\u00a0al. 2023. Clinical text summarization: Adapting large language models can outperform human experts. arXiv:2309.07430. DOI:10.48550\/ARXIV.2309.07430","DOI":"10.48550\/ARXIV.2309.07430"},{"key":"e_1_3_2_232_2","doi-asserted-by":"publisher","unstructured":"Sai Vemprala Rogerio Bonatti Arthur Bucker and Ashish Kapoor. 2024. ChatGPT for robotics: Design principles and model abilities. IEEE Access 12 (2024) 55682\u201355696. DOI:10.1109\/ACCESS.2024.3387941","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"e_1_3_2_233_2","doi-asserted-by":"publisher","unstructured":"Boshi Wang Xiang Deng and Huan Sun. 2022. Iteratively prompt pre-trained language models for chain of thought. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing EMNLP 2022 Abu Dhabi United Arab Emirates December 7-11 2022. Association for Computational Linguistics 2714\u20132730. DOI:10.18653\/V1\/2022.EMNLP-MAIN.174","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.174"},{"key":"e_1_3_2_234_2","doi-asserted-by":"publisher","unstructured":"Cunxiang Wang Pai Liu and Yue Zhang. 2021. Can generative pre-trained language models serve as knowledge bases for closed-book QA? In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics Online 3241\u20133251. DOI:10.18653\/v1\/2021.acl-long.251","DOI":"10.18653\/v1\/2021.acl-long.251"},{"key":"e_1_3_2_235_2","doi-asserted-by":"publisher","unstructured":"Duolin Wang Mahdi Pourmirzaei Usman L. Abbas Shuai Zeng Negin Manshour Farzaneh Esmaili Biplab Poudel Yuexu Jiang Qing Shao Jin Chen and Dong Xu. 2025. S-PLM: Structure-aware protein language model via contrastive learning between sequence and structure. Advanced Science 12 5 (2025) 2404212. DOI:10.1002\/advs.202404212","DOI":"10.1002\/advs.202404212"},{"key":"e_1_3_2_236_2","unstructured":"Guanzhi Wang Yuqi Xie Yunfan Jiang Ajay Mandlekar Chaowei Xiao Yuke Zhu Linxi Fan and Anima Anandkumar. 2024. Voyager: An open-ended embodied agent with large language models. Trans. Mach. Learn. Res. 2024 (2024). https:\/\/openreview.net\/forum?id=ehfRiF0R3a"},{"key":"e_1_3_2_237_2","unstructured":"Heng Wang Shangbin Feng Tianxing He Zhaoxuan Tan Xiaochuang Han and Yulia Tsvetkov. 2023. Can language models solve graph problems in natural language? In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10-16 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/622afc4edf2824a1b6aaf5afe153fa93-Abstract-Conference.html"},{"key":"e_1_3_2_238_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3343123"},{"key":"e_1_3_2_239_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"e_1_3_2_240_2","doi-asserted-by":"publisher","unstructured":"Lei Wang Songheng Zhang Yun Wang Ee-Peng Lim and Yong Wang. 2023. LLM4Vis: Explainable visualization recommendation using ChatGPT. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: EMNLP 2023 - Industry Track Singapore December 6-10 2023. Association for Computational Linguistics 675\u2013692. DOI:10.18653\/V1\/2023.EMNLP-INDUSTRY.64","DOI":"10.18653\/V1\/2023.EMNLP-INDUSTRY.64"},{"key":"e_1_3_2_241_2","doi-asserted-by":"publisher","unstructured":"Siyuan Wang Bo Peng Yichao Liu and Qi Peng. 2023. Fine-grained medical vision-language representation learning for radiology report generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 15949\u201315956. DOI:10.18653\/V1\/2023.EMNLP-MAIN.989","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.989"},{"key":"e_1_3_2_242_2","doi-asserted-by":"publisher","unstructured":"Sheng Wang Zihao Zhao Xi Ouyang Qian Wang and Dinggang Shen. 2023. ChatCAD: Interactive computer-aided diagnosis on medical image using large language models. arXiv:2302.07257. DOI:10.48550\/ARXIV.2302.07257","DOI":"10.48550\/ARXIV.2302.07257"},{"key":"e_1_3_2_243_2","doi-asserted-by":"publisher","unstructured":"Wenkai Wang Zhenling Peng and Jianyi Yang. 2022. Single-sequence protein structure prediction using supervised transformer protein language models. Nat. Comput. Sci. 2 12 (2022) 804\u2013814. DOI:10.1038\/S43588-022-00373-3","DOI":"10.1038\/S43588-022-00373-3"},{"key":"e_1_3_2_244_2","doi-asserted-by":"publisher","unstructured":"Xidong Wang Guiming Chen Dingjie Song Zhiyi Zhang Zhihong Chen Qingying Xiao Junying Chen Feng Jiang Jianquan Li Xiang Wan et\u00a0al. 2024. CMB: A comprehensive medical benchmark in chinese. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) NAACL 2024 Mexico City Mexico June 16-21 2024. Association for Computational Linguistics 6184\u20136205. DOI:10.18653\/V1\/2024.NAACL-LONG.343","DOI":"10.18653\/V1\/2024.NAACL-LONG.343"},{"key":"e_1_3_2_245_2","unstructured":"Zihao Wang Shaofei Cai Anji Liu Xiaojian Ma and Yitao Liang. 2023. Describe explain plan and select: Interactive planning with large language models enables open-world multi-task agents. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10-16 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/6b8dfb8c0c12e6fafc6c256cb08a5ca7-Abstract-Conference.html"},{"key":"e_1_3_2_246_2","doi-asserted-by":"publisher","unstructured":"Zhenhailong Wang Shaoguang Mao Wenshan Wu Tao Ge Furu Wei and Heng Ji. 2024. Unleashing cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) NAACL 2024 Mexico City Mexico June 16-21 2024. Association for Computational Linguistics 257\u2013279. DOI:10.18653\/V1\/2024.NAACL-LONG.15","DOI":"10.18653\/V1\/2024.NAACL-LONG.15"},{"key":"e_1_3_2_247_2","doi-asserted-by":"publisher","unstructured":"NoahWang Zhongyuan Peng Haoran Que Jiaheng Liu Wangchunshu Zhou YuhanWu Hongcheng Guo Ruitong Gan Zehao Ni Jian Yang et\u00a0al. 2024. RoleLLM: Benchmarking eliciting and enhancing role-playing abilities of large language models. In Findings of the Association for Computational Linguistics ACL 2024 Bangkok Thailand and virtual meeting August 11-16 2024. Association for Computational Linguistics 14743\u201314777. DOI:10.18653\/V1\/2024.FINDINGS-ACL.878","DOI":"10.18653\/V1\/2024.FINDINGS-ACL.878"},{"key":"e_1_3_2_248_2","unstructured":"Jason Wei Maarten Bosma Vincent Zhao Kelvin Guu Adams Wei Yu Brian Lester Nan Du Andrew M. Dai and Quoc V. Le. 2022. Finetuned language models are zero-shot learners. In The Tenth International Conference on Learning Representations ICLR 2022 Virtual Event April 25-29 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=gEZrGCozdqR"},{"key":"e_1_3_2_249_2","doi-asserted-by":"publisher","unstructured":"Jimmy Wei Kurt Shuster Arthur Szlam Jason Weston Jack Urbanek and Mojtaba Komeili. 2023. Multi-party chat: Conversational agents in group settings with humans and models. arXiv:2304.13835. DOI:10.48550\/ARXIV.2304.13835","DOI":"10.48550\/ARXIV.2304.13835"},{"key":"e_1_3_2_250_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter Fei Xia Ed H. Chi Quoc V Le and Denny Zhou. 2022. Chain of thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems 35:Annual Conference on Neural Information Processing Systems 2022 NeurIPS 2022 New Orleans LA USA November 28 - December 9 2022. http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html"},{"key":"e_1_3_2_251_2","doi-asserted-by":"publisher","unstructured":"Yuxiang Wei Zhe Wang Jiawei Liu Yifeng Ding and Lingming Zhang. 2023. Magicoder: Source code is all you need. arXiv:2312.02120. DOI:10.48550\/ARXIV.2312.02120","DOI":"10.48550\/ARXIV.2312.02120"},{"key":"e_1_3_2_252_2","doi-asserted-by":"publisher","unstructured":"Yuxiang Wei Chunqiu Steven Xia and Lingming Zhang. 2023. Copiloting the copilots: Fusing large language models with completion engines for automated program repair. In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC\/FSE 2023 San Francisco CA USA December 3-9 2023. ACM 172\u2013184. DOI:10.1145\/3611643.3616271","DOI":"10.1145\/3611643.3616271"},{"key":"e_1_3_2_253_2","doi-asserted-by":"publisher","unstructured":"Chaoyi Wu Xiaoman Zhang Ya Zhang Yanfeng Wang and Weidi Xie. 2023. Towards generalist foundation model for radiology. arXiv:2308.02463. DOI:10.48550\/ARXIV.2308.02463","DOI":"10.48550\/ARXIV.2308.02463"},{"key":"e_1_3_2_254_2","doi-asserted-by":"publisher","unstructured":"Rui Min Wu Fan Ding Rui Wang Rui Shen Xiwen Zhang Shitong Luo Chenpeng Su Zuofan Wu Qi Xie et\u00a0al. 2022. High-resolution de novo structure prediction from primary sequence. BioRxiv (2022) 2022\u201307. DOI:10.1101\/2022.07.21.500999","DOI":"10.1101\/2022.07.21.500999"},{"key":"e_1_3_2_255_2","doi-asserted-by":"publisher","unstructured":"Shijie Wu Ozan Irsoy Steven Lu Vadim Dabravolski Mark Dredze Sebastian Gehrmann Prabhanjan Kambadur David S. Rosenberg and Gideon Mann. 2023. BloombergGPT: A large language model for finance. arXiv:2303.17564. DOI:10.48550\/ARXIV.2303.17564","DOI":"10.48550\/ARXIV.2303.17564"},{"key":"e_1_3_2_256_2","doi-asserted-by":"publisher","unstructured":"Zhiheng Xi Wenxiang Chen Xin Guo Wei He Yiwen Ding Boyang Hong Ming Zhang Junzhe Wang Senjie Jin Enyu Zhou et\u00a0al. 2025. The rise and potential of large language model based agents: A survey. Sci. China Inf. Sci. 68 2 (2025). DOI:10.1007\/S11432-024-4222-0","DOI":"10.1007\/S11432-024-4222-0"},{"key":"e_1_3_2_257_2","doi-asserted-by":"publisher","unstructured":"Chunqiu Steven Xia and Lingming Zhang. 2023. Conversational automated program repair. arXiv:2301.13246. DOI:10.48550\/ARXIV.2301.13246","DOI":"10.48550\/ARXIV.2301.13246"},{"key":"e_1_3_2_258_2","doi-asserted-by":"publisher","unstructured":"Chunqiu Steven Xia and Lingming Zhang. 2023. Keep the conversation going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT. arXiv:2304.00385. DOI:10.48550\/ARXIV.2304.00385","DOI":"10.48550\/ARXIV.2304.00385"},{"key":"e_1_3_2_259_2","doi-asserted-by":"publisher","unstructured":"Qianqian Xie Weiguang Han Yanzhao Lai Min Peng and Jimin Huang. 2023. The wall street neophyte: A zero-shot analysis of ChatGPT Over MultiModal stock movement prediction challenges. arXiv:2304.05351. DOI:10.48550\/ARXIV.2304.05351","DOI":"10.48550\/ARXIV.2304.05351"},{"key":"e_1_3_2_260_2","doi-asserted-by":"publisher","unstructured":"Qianqian Xie Weiguang Han Xiao Zhang Yanzhao Lai Min Peng Alejandro Lopez-Lira and Jimin Huang. 2023. PIXIU: A large language model instruction data and evaluation benchmark for finance. arXiv:2306.05443. DOI:10.48550\/ARXIV.2306.05443","DOI":"10.48550\/ARXIV.2306.05443"},{"key":"e_1_3_2_261_2","doi-asserted-by":"publisher","unstructured":"Yinghao Chen Zehao Hu Chen Zhi Junxiao Han Shuiguang Deng and Jianwei Yin. 2024. ChatUniTest: A framework for LLM-based test generation. In Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering FSE 2024 Porto de Galinhas Brazil July 15-19 2024. ACM 572\u2013576. DOI:10.1145\/3663529.3663801","DOI":"10.1145\/3663529.3663801"},{"key":"e_1_3_2_262_2","doi-asserted-by":"publisher","unstructured":"Zhenchang Xing Qing Huang Yu Cheng Liming Zhu Qinghua Lu and Xiwei Xu. 2023. Prompt sapper: LLM-empowered software engineering infrastructure for AI-Native services. arXiv:2306.02230. DOI:10.48550\/ARXIV.2306.02230","DOI":"10.48550\/ARXIV.2306.02230"},{"key":"e_1_3_2_263_2","unstructured":"Minghao Xu Xinyu Yuan Santiago Miret and Jian Tang. 2023. ProtST: Multi-modality learning of protein sequences and biomedical texts. In International Conference on Machine Learning ICML 2023 23-29 July 2023 Honolulu Hawaii USA (Proceedings of Machine Learning Research Vol. 202). PMLR 38749\u201338767. https:\/\/proceedings.mlr.press\/v202\/xu23t.html"},{"key":"e_1_3_2_264_2","doi-asserted-by":"publisher","unstructured":"Junbing Yan Chengyu Wang Taolin Zhang Xiaofeng He Jun Huang and Wei Zhang. 2023. From complex to simple: Unraveling the cognitive tree for reasoning with small language models. In Findings of the Association for Computational Linguistics: EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 12413\u201312425. DOI:10.18653\/V1\/2023.FINDINGS-EMNLP.828","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.828"},{"key":"e_1_3_2_265_2","doi-asserted-by":"publisher","unstructured":"Kevin Yang Dan Klein Nanyun Peng and Yuandong Tian. 2023. DOC: Improving long story coherence with detailed outline control. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics Toronto Canada 3378\u20133465. DOI:10.18653\/v1\/2023.acl-long.190","DOI":"10.18653\/v1\/2023.acl-long.190"},{"key":"e_1_3_2_266_2","doi-asserted-by":"publisher","unstructured":"Kevin Yang Yuandong Tian Nanyun Peng and Dan Klein. 2022. Re3: Generating longer stories with recursive reprompting and revision. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing EMNLP 2022 Abu Dhabi United Arab Emirates December 7-11 2022. Association for Computational Linguistics 4393\u20134479. DOI:10.18653\/V1\/2022.EMNLP-MAIN.296","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.296"},{"key":"e_1_3_2_267_2","doi-asserted-by":"publisher","unstructured":"Yizhe Yang Huashan Sun Jiawei Li Runheng Liu Yinghao Li Yuhang Liu Heyan Huang and Yang Gao. 2023. MindLLM: Pre-training lightweight large language model from scratch evaluations and domain applications. arXiv:2310.15777. DOI:10.48550\/ARXIV.2310.15777","DOI":"10.48550\/ARXIV.2310.15777"},{"key":"e_1_3_2_268_2","unstructured":"Shunyu Yao Howard Chen John Yang and Karthik Narasimhan. 2022. WebShop: Towards scalable real-world web interaction with grounded language agents. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 NeurIPS 2022 New Orleans LA USA November 28 - December 9 2022. http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/82ad13ec01f9fe44c01cb91814fd7b8c-Abstract-Conference.html"},{"key":"e_1_3_2_269_2","doi-asserted-by":"publisher","unstructured":"Seonghyeon Ye Hyeonbin Hwang Sohee Yang Hyeongu Yun Yireun Kim and Minjoon Seo. 2023. In-context instruction learning. arXiv:2302.14691. DOI:10.48550\/ARXIV.2302.14691","DOI":"10.48550\/ARXIV.2302.14691"},{"key":"e_1_3_2_270_2","doi-asserted-by":"publisher","unstructured":"Caiyang Yu Xianggen Liu Wentao Feng Chenwei Tang and Jiancheng Lv. 2023. GPT-NAS: Evolutionary neural architecture search with the generative pre-trained model. arXiv:2305.05351. DOI:10.48550\/ARXIV.2305.05351","DOI":"10.48550\/ARXIV.2305.05351"},{"key":"e_1_3_2_271_2","doi-asserted-by":"publisher","unstructured":"Dingyao Yu Kaitao Song Peiling Lu Tianyu He Xu Tan Wei Ye Shikun Zhang and Jiang Bian. 2023. MusicAgent: An AI agent for music understanding and generation with large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing EMNLP 2023 - System Demonstrations Singapore December 6-10 2023. Association for Computational Linguistics 246\u2013255. DOI:10.18653\/V1\/2023.EMNLP-DEMO.21","DOI":"10.18653\/V1\/2023.EMNLP-DEMO.21"},{"key":"e_1_3_2_272_2","doi-asserted-by":"publisher","unstructured":"Fangyi Yu Lee Quartey and Frank Schilder. 2022. Legal prompting: Teaching a language model to think like a lawyer. arXiv:2212.01326. DOI:10.48550\/ARXIV.2212.01326","DOI":"10.48550\/ARXIV.2212.01326"},{"key":"e_1_3_2_273_2","unstructured":"Jifan Yu Xiaozhi Wang Shangqing Tu Shulin Cao Daniel Zhang-Li Xin Lv Hao Peng Zijun Yao Xiaohan Zhang Hanming Li et\u00a0al. 2024. KoLA: Carefully benchmarking world knowledge of large language models. In The Twelfth International Conference on Learning Representations ICLR 2024 Vienna Austria May 7-11 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=AqN23oqraW"},{"key":"e_1_3_2_274_2","doi-asserted-by":"publisher","unstructured":"Yangyang Yu Haohang Li Zhi Chen Yuechen Jiang Yang Li Denghui Zhang Rong Liu Jordan W. Suchow and Khaldoun Khashanah. 2023. FinMe: A performance-enhanced large language model trading agent with layered memory and character design. arXiv:2311.13743. DOI:10.48550\/ARXIV.2311.13743","DOI":"10.48550\/ARXIV.2311.13743"},{"key":"e_1_3_2_275_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511105"},{"key":"e_1_3_2_276_2","doi-asserted-by":"publisher","unstructured":"Haoqi Yuan Chi Zhang Hongcheng Wang Feiyang Xie Penglin Cai Hao Dong and Zongqing Lu. 2023. Plan4MC: Skill reinforcement learning and planning for open-world minecraft tasks. arXiv:2303.16563. DOI:10.48550\/ARXIV.2303.16563","DOI":"10.48550\/ARXIV.2303.16563"},{"key":"e_1_3_2_277_2","doi-asserted-by":"publisher","unstructured":"Shengbin Yue Wei Chen Siyuan Wang Bingxuan Li Chenchen Shen Shujun Liu Yuxuan Zhou Yao Xiao Song Yun Xuanjing Huang and Zhongyu Wei. 2023. DISC-LawLLM: Fine-tuning large language models for intelligent legal services. (2023). arXiv:2309.11325. DOI:10.48550\/ARXIV.2309.11325","DOI":"10.48550\/ARXIV.2309.11325"},{"key":"e_1_3_2_278_2","doi-asserted-by":"publisher","unstructured":"Daoguang Zan Bei Chen Fengji Zhang Dianjie Lu Bingchao Wu Bei Guan Yongji Wang and Jian-Guang Lou. 2023. Large language models meet NL2Code: A survey. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics Toronto Canada 7443\u20137464. DOI:10.18653\/v1\/2023.acl-long.411","DOI":"10.18653\/v1\/2023.acl-long.411"},{"key":"e_1_3_2_279_2","doi-asserted-by":"publisher","unstructured":"Hongbo Zhang Junying Chen Feng Jiang Fei Yu Zhihong Chen Guiming Chen Jianquan Li XiangboWu Zhiyi Zhang Qingying Xiao et\u00a0al. 2023. HuatuoGPT towards taming language model to be a doctor. In Findings of the Association for Computational Linguistics: EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 10859\u201310885. DOI:10.18653\/V1\/2023.FINDINGSEMNLP.725","DOI":"10.18653\/V1\/2023.FINDINGSEMNLP.725"},{"key":"e_1_3_2_280_2","doi-asserted-by":"publisher","unstructured":"Kechi Zhang Zhuo Li Jia Li Ge Li and Zhi Jin. 2023. Self-Edit: Fault-aware code editor for code generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics Toronto Canada 769\u2013787. DOI:10.18653\/v1\/2023.acl-long.45","DOI":"10.18653\/v1\/2023.acl-long.45"},{"key":"e_1_3_2_281_2","unstructured":"Ningyu Zhang Zhen Bi Xiaozhuan Liang Siyuan Cheng Haosen Hong Shumin Deng Jiazhang Lian Qiang Zhang and Huajun Chen. 2022. OntoProtein: Protein pretraining with gene ontology embedding. In The Tenth International Conference on Learning Representations ICLR 2022 Virtual Event April 25-29 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=yfe1VMYAXa4"},{"key":"e_1_3_2_282_2","doi-asserted-by":"publisher","unstructured":"Xuanyu Zhang and Qing Yang. 2023. XuanYuan 2.0: A large Chinese financial chat model with hundreds of billions parameters. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management CIKM 2023 Birmingham United Kingdom October 21-25 2023. ACM 4435\u20134439. DOI:10.1145\/3583780.3615285","DOI":"10.1145\/3583780.3615285"},{"key":"e_1_3_2_283_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.622"},{"key":"e_1_3_2_284_2","doi-asserted-by":"publisher","unstructured":"Yuwei Zhang Zhi Jin Ying Xing and Ge Li. 2023. STEAM: Simulating the in Tractive BEhavior of ProgrAMmers for Automatic Bug Fixing. (2023). arXiv:2308.14460. DOI:10.48550\/ARXIV.2308.14460","DOI":"10.48550\/ARXIV.2308.14460"},{"key":"e_1_3_2_285_2","doi-asserted-by":"publisher","unstructured":"Yuchen Zhang Mingsheng Long Kaiyuan Chen Lanxiang Xing Ronghua Jin Michael I. Jordan and Jianmin Wang. 2023. Skilful nowcasting of extreme precipitation with NowcastNet. Nat. 619 7970 (2023) 526\u2013532. DOI:10.1038\/S41586-023-06184-4","DOI":"10.1038\/S41586-023-06184-4"},{"key":"e_1_3_2_286_2","doi-asserted-by":"publisher","unstructured":"Ziyin Zhang Chaoyu Chen Bingchang Liu Cong Liao Zi Gong Hang Yu Jianguo Li and Rui Wang. 2023. A survey on language models for code. arXiv:2311.07989. DOI:10.48550\/ARXIV.2311.07989","DOI":"10.48550\/ARXIV.2311.07989"},{"key":"e_1_3_2_287_2","unstructured":"Zuobai Zhang Minghao Xu Arian Rokkum Jamasb Vijil Chenthamarakshan Aur\u00e9lie C. Lozano Payel Das and Jian Tang. 2022. Protein representation learning by geometric structure pretraining. In The Eleventh International Conference on Learning Representations ICLR 2023 Kigali Rwanda May 1-5 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=to3qCB3tOh9"},{"key":"e_1_3_2_288_2","doi-asserted-by":"publisher","unstructured":"Bowen Zhao Changkai Ji Yuejie Zhang Wen He Yingwen Wang Qing Wang Rui Feng and Xiaobo Zhang. 2023. Large language models are complex table parsers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 14786\u201314802. DOI:10.18653\/V1\/2023.EMNLP-MAIN.914","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.914"},{"key":"e_1_3_2_289_2","doi-asserted-by":"publisher","unstructured":"Guosheng Zhao Yan Yan and Zijian Zhao. 2023. Normal-abnormal decoupling memory for medical report generation. In Findings of the Association for Computational Linguistics: EMNLP 2023 Singapore December 6-10 2023. Association for Computational Linguistics 1962\u20131977. DOI:10.18653\/V1\/2023.FINDINGS-EMNLP.131","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.131"},{"key":"e_1_3_2_290_2","doi-asserted-by":"publisher","unstructured":"Junjie Zhao Xiang Chen Guang Yang and Yiheng Shen. 2023. Automatic smart contract comment generation via large language models and in-context learning. Inf. Softw. Technol. 168 (2024) 107405. DOI:10.1016\/J.INFSOF.2024.107405","DOI":"10.1016\/J.INFSOF.2024.107405"},{"key":"e_1_3_2_291_2","doi-asserted-by":"publisher","unstructured":"Yilun Zhao Yitao Long Hongjun Liu Ryo Kamoi Linyong Nan Lyuhao Chen Yixin Liu Xiangru Tang Rui Zhang and Arman Cohan. 2024. DocMath-Eval: Evaluating math reasoning capabilities of LLMs in understanding financial documents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ACL 2024 Bangkok Thailand August 11-16 2024. Association for Computational Linguistics 16103\u201316120. DOI:10.18653\/V1\/2024.ACL-LONG.852","DOI":"10.18653\/V1\/2024.ACL-LONG.852"},{"key":"e_1_3_2_292_2","unstructured":"Zirui Zhao Wee Sun Lee and David Hsu. 2023. Large language models as commonsense knowledge for large-scale task planning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10-16 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/65a39213d7d0e1eb5d192aa77e77eeb7-Abstract-Conference.html"},{"key":"e_1_3_2_293_2","unstructured":"Zihao Zhao Eric Wallace Shi Feng Dan Klein and Sameer Singh. 2021. Calibrate before use: Improving few-shot performance of language models. In Proceedings of the 38th International Conference on Machine Learning ICML 2021 18-24 July 2021 Virtual Event (Proceedings of Machine Learning Research Vol. 139). PMLR 12697\u201312706. http:\/\/proceedings.mlr.press\/v139\/zhao21c.html"},{"key":"e_1_3_2_294_2","doi-asserted-by":"publisher","unstructured":"Mingkai Zheng Xiu Su Shan You Fei Wang Chen Qian Chang Xu and Samuel Albanie. 2023. Can GPT-4 perform neural architecture search? arXiv:2304.10970. DOI:10.48550\/ARXIV.2304.10970","DOI":"10.48550\/ARXIV.2304.10970"},{"key":"e_1_3_2_295_2","doi-asserted-by":"publisher","unstructured":"Ruiqi Zhong Kristy Lee Zheng Zhang and Dan Klein. 2021. Adapting language models for zero-shot learning by meta-tuning on dataset and prompt collections. In Findings of the Association for Computational Linguistics: EMNLP 2021 Virtual Event\/Punta Cana Dominican Republic 16-20 November 2021. Association for Computational Linguistics 2856\u20132878. DOI:10.18653\/V1\/2021.FINDINGSEMNLP.244","DOI":"10.18653\/V1\/2021.FINDINGSEMNLP.244"},{"key":"e_1_3_2_296_2","unstructured":"Hattie Zhou Arwen Bradley Etai Littwin Noam Razin Omid Saremi Josh Susskind Samy Bengio and Preetum Nakkiran. 2024. What algorithms can transformers learn? A study in length generalization. In The Twelfth International Conference on Learning Representations ICLR 2024 Vienna Austria May 7-11 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=AssIuHnmHX"},{"key":"e_1_3_2_297_2","doi-asserted-by":"publisher","unstructured":"Caleb Ziems William Held Omar Shaikh Jiaao Chen Zhehao Zhang and Diyi Yang. 2023. Can large language models transform computational social science?Comput. Linguistics 50 1 (2024) 237\u2013291. DOI:10.1162\/COLI_A_00502","DOI":"10.1162\/COLI_A_00502"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3735632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T03:24:11Z","timestamp":1757474651000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3735632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":296,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3735632"],"URL":"https:\/\/doi.org\/10.1145\/3735632","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2024-06-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}