{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T12:20:38Z","timestamp":1776082838297,"version":"3.50.1"},"reference-count":210,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2026,2,28]]},"abstract":"<jats:p>Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task-agnostic foundation for a wide range of applications. However, directly applying LLMs to solve sophisticated problems in specific domains meets many hurdles, caused by the heterogeneity of domain data, the sophistication of domain knowledge, the uniqueness of domain objectives, and the diversity of the constraints (e.g., various social norms, cultural conformity, religious beliefs, and ethical standards in the domain applications). Domain specification techniques are key to making large language models disruptive in many applications. Specifically, to solve these hurdles, there has been a notable increase in research and practices conducted in recent years on the domain specialization of LLMs. This emerging field of study, with its substantial potential for impact, necessitates a comprehensive and systematic review to summarize better and guide ongoing work in this area. In this article, we present a comprehensive survey on domain specification techniques for large language models, an emerging direction critical for large language model applications. First, we propose a systematic taxonomy that categorizes the LLM domain-specialization techniques based on the accessibility to LLMs and summarizes the framework for all the subcategories as well as their relations and differences to each other. Second, we present an extensive taxonomy of critical application domains that can benefit dramatically from specialized LLMs, discussing their practical significance and open challenges. Last, we offer our insights into the current research status and future trends in this area.<\/jats:p>","DOI":"10.1145\/3764579","type":"journal-article","created":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T11:05:31Z","timestamp":1756897531000},"page":"1-39","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey"],"prefix":"10.1145","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8044-6026","authenticated-orcid":false,"given":"Chen","family":"Ling","sequence":"first","affiliation":[{"name":"Computer Science, Emory University","place":["Atlanta, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4950-4018","authenticated-orcid":false,"given":"Xujiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"NEC Laboratories America Inc","place":["Princeton, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9052-6951","authenticated-orcid":false,"given":"Jiaying","family":"Lu","sequence":"additional","affiliation":[{"name":"Computer Science, Emory University","place":["Atlanta, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2586-3430","authenticated-orcid":false,"given":"Chengyuan","family":"Deng","sequence":"additional","affiliation":[{"name":"Rutgers The State University of New Jersey","place":["New Brunswick, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1532-0712","authenticated-orcid":false,"given":"Can","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Pittsburgh","place":["Pittsburgh, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6635-4296","authenticated-orcid":false,"given":"Junxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"NEC Laboratories America Inc","place":["Princeton, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3421-2410","authenticated-orcid":false,"given":"Tanmoy","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"George Mason University","place":["Fairfax, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3205-8464","authenticated-orcid":false,"given":"Yun","family":"Li","sequence":"additional","affiliation":[{"name":"George Mason University","place":["Fairfax, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6388-2619","authenticated-orcid":false,"given":"Hejie","family":"Cui","sequence":"additional","affiliation":[{"name":"Computer Science, Emory University","place":["Atlanta, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1492-0476","authenticated-orcid":false,"given":"Xuchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Research","place":["Redmond, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1274-626X","authenticated-orcid":false,"given":"Tianjiao","family":"Zhao","sequence":"additional","affiliation":[{"name":"BlackRock Inc","place":["Atlanta, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6879-6124","authenticated-orcid":false,"given":"Amit","family":"Panalkar","sequence":"additional","affiliation":[{"name":"BlackRock Inc","place":["Atlanta, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1040-9032","authenticated-orcid":false,"given":"Dhagash","family":"Mehta","sequence":"additional","affiliation":[{"name":"Black Rock Inc","place":["Chiyoda, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8005-3207","authenticated-orcid":false,"given":"Stefano","family":"Pasquali","sequence":"additional","affiliation":[{"name":"BlackRock Inc","place":["New York, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5456-626X","authenticated-orcid":false,"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[{"name":"NEC Laboratories America Inc","place":["Princeton, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3604-4799","authenticated-orcid":false,"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"NEC Laboratories America Inc","place":["Princeton, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4396-5139","authenticated-orcid":false,"given":"Yanchi","family":"Liu","sequence":"additional","affiliation":[{"name":"NEC Laboratories America Inc","place":["Princeton, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6803-0535","authenticated-orcid":false,"given":"Zhengzhang","family":"Chen","sequence":"additional","affiliation":[{"name":"NEC Laboratories America Inc","place":["Princeton, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9363-738X","authenticated-orcid":false,"given":"Haifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"NEC Laboratories America Inc","place":["Princeton, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6539-9549","authenticated-orcid":false,"given":"Chris","family":"White","sequence":"additional","affiliation":[{"name":"NEC Laboratories America Inc","place":["Princeton, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9830-793X","authenticated-orcid":false,"given":"Quanquan","family":"Gu","sequence":"additional","affiliation":[{"name":"University of California Los Angeles","place":["Los Angeles, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2200-8711","authenticated-orcid":false,"given":"Jian","family":"Pei","sequence":"additional","affiliation":[{"name":"Duke University","place":["Durham, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9145-4531","authenticated-orcid":false,"given":"Carl","family":"Yang","sequence":"additional","affiliation":[{"name":"Computer Science, Emory University","place":["Atlanta, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2648-9989","authenticated-orcid":false,"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Computer Science, Emory University","place":["Atlanta, United States"]}]}],"member":"320","published-online":{"date-parts":[[2025,10,6]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Armen Aghajanyan Sonal Gupta and Luke Zettlemoyer. 2021. Intrinsic dimensionality explains the effectiveness of language model fine-tuning. 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).","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"e_1_3_2_3_2","first-page":"242","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Allen-Zhu Zeyuan","year":"2019","unstructured":"Zeyuan Allen-Zhu, Yuanzhi Li, and Zhao Song. 2019. A convergence theory for deep learning via over-parameterization. In Proceedings of the International Conference on Machine Learning. 242\u2013252."},{"key":"e_1_3_2_4_2","volume-title":"Proceedings of the ICLR","author":"Arora Simran","year":"2023","unstructured":"Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel Orr, Neel Guha, Kush Bhatia, Ines Chami, and Christopher Re. 2023. Ask me anything: A simple strategy for prompting language models. In Proceedings of the ICLR."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.446"},{"key":"e_1_3_2_6_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Asai Akari","year":"2024","unstructured":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to retrieve, generate, and critique through self-reflection. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_2_7_2","unstructured":"Zhangir Azerbayev Ansong Ni Hailey Schoelkopf and Dragomir Radev. 2022. Explicit knowledge transfer for weakly-supervised code generation. arXiv:2211.16740. Retrieved from https:\/\/arxiv.org\/abs\/2211.16740"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Yejin Bang Samuel Cahyawijaya Nayeon Lee Wenliang Dai Dan Su Bryan Wilie Holy Lovenia Ziwei Ji Tiezheng Yu Willy Chung Quyet V. Do Yan Xu and Pascale Fung. 2023. A multitask multilingual multimodal evaluation of ChatGPT on reasoning hallucination and interactivity. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). Nusa Dua Bali. Association for Computational Linguistics 675\u2013718.","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Ankur Bapna and Orhan Firat. 2019. Simple scalable adaptation for neural machine translation. 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) Hong Kong China. Association for Computational Linguistics 1538\u20131548.","DOI":"10.18653\/v1\/D19-1165"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00468"},{"key":"e_1_3_2_11_2","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Bhardwaj Rishabh","year":"2022","unstructured":"Rishabh Bhardwaj, Amrita Saha, and Steven C. H. Hoi. 2022. Vector-quantized input-contextualized soft prompts for natural language understanding. In Proceedings of the Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_12_2","first-page":"2206","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Borgeaud Sebastian","year":"2022","unstructured":"Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et\u00a0al. 2022. Improving language models by retrieving from trillions of tokens. In Proceedings of the International Conference on Machine Learning. 2206\u20132240."},{"key":"e_1_3_2_13_2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","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, Amanda Askell, et\u00a0al. 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems 33 (2020), 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_14_2","unstructured":"Lucas Page-Caccia Edoardo Maria Ponti Zhan Su Matheus Pereira Nicolas Le Roux and Alessandro Sordoni. 2023. Multi-head adapter routing for cross-task generalization. Advances in Neural Information Processing Systems 36 (2023) 56916\u201356931."},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Yihan Cao Siyu Li Yixin Liu Zhiling Yan Yutong Dai Philip Yu and Lichao Sun. 2025. A survey of AI-generated content (aigc). ACM Computing Surveys 57 5 (2025) 1\u201338.","DOI":"10.1145\/3704262"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Sanyuan Chen Yutai Hou Yiming Cui Wanxiang Che Ting Liu and Xiangzhan Yu. 2020. Recall and Learn: Fine-tuning deep pretrained language models with less forgetting. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics 7870\u20137881.","DOI":"10.18653\/v1\/2020.emnlp-main.634"},{"key":"e_1_3_2_18_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. Transactions on Machine Learning Research (2023) 2835\u20138856."},{"key":"e_1_3_2_19_2","article-title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","author":"Chen Xiang","year":"2021","unstructured":"Xiang Chen, Ningyu Zhang, Ningyu Zhang, Xin Xie, Shumin Deng, Yunzhi Yao, Chuanqi Tan, Fei Huang, Luo Si, and Huajun Chen. 2021. KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction. In Proceedings of the ACM Web Conference 2022.","journal-title":"In Proceedings of the ACM Web Conference 2022."},{"key":"e_1_3_2_20_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Cheng Zhoujun","year":"2023","unstructured":"Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, et\u00a0al. 2023. Binding language models in symbolic languages. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_21_2","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham et\u00a0al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24 240 (2023) 1\u2013113."},{"key":"e_1_3_2_22_2","unstructured":"Christiano et\u00a0al. 2017. Deep reinforcement learning from human preferences. NeurIPS 2017. 4299\u20134307."},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Alexandra Chronopoulou Matthew E. Peters Alexander Fraser and Jesse Dodge. 2023. AdapterSoup: Weight averaging to improve generalization of pretrained language models. In Findings of the Association for Computational Linguistics: EACL. 2054\u20132063.","DOI":"10.18653\/v1\/2023.findings-eacl.153"},{"key":"e_1_3_2_24_2","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li et\u00a0al. 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research 25 70 (2024) 1\u201353."},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Hejie Cui Jiaying Lu Ran Xu Shiyu Wang Wenjing Ma Yue Yu Shaojun Yu Xuan Kan Chen Ling Liang Zhao Zhaohui S. Qin Joyce C. Ho Tianfan Fu Jing Ma Mengdi Huai Fei Wang and Carl Yang. 2025. A review on knowledge graphs for healthcare: Resources applications and promises. Journal of Biomedical Informatics 169 (2025) 104861.","DOI":"10.1016\/j.jbi.2025.104861"},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Damai Dai Li Dong Yaru Hao Zhifang Sui Baobao Chang and Furu Wei. 2022. Knowledge neurons in pretrained transformers. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 8493\u20138502.","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"e_1_3_2_27_2","unstructured":"Zhuyun Dai Vincent Y. Zhao Ji Ma Yi Luan Jianmo Ni Jing Lu Anton Bakalov Kelvin Guu Keith Hall and Ming-Wei Chang. 2022. Promptagator: Few-shot Dense Retrieval From 8 Examples. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_28_2","volume-title":"Proceedings of the 2nd Workshop on Language and Reinforcement Learning","author":"Dasgupta Ishita","year":"2023","unstructured":"Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino, Arun Ahuja, Sheila Babayan, Felix Hill, and Rob Fergus. 2023. Collaborating with language models for embodied reasoning. In Proceedings of the 2nd Workshop on Language and Reinforcement Learning."},{"key":"e_1_3_2_29_2","volume-title":"Proceedings of the 2021 EMNLP","author":"Cao Nicola De","year":"2021","unstructured":"Nicola De Cao, Wilker Aziz, and Ivan Titov. 2021. Editing factual knowledge in language models. In Proceedings of the 2021 EMNLP."},{"key":"e_1_3_2_30_2","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Deng Mingkai","year":"2022","unstructured":"Mingkai Deng, Jianyu Wang, Cheng-Ping Hsieh, Yihan Wang, Han Guo, Tianmin Shu, Meng Song, Eric P. Xing, and Zhiting Hu. 2022. RLPrompt: Optimizing discrete text prompts with reinforcement learning. In Proceedings of the Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_31_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Volume 1 (Long and Short Papers). 4171\u20134186."},{"key":"e_1_3_2_32_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Drozdov Andrew","year":"2023","unstructured":"Andrew Drozdov, Nathanael Sch\u00e4rli, Ekin Aky\u00fcrek, Nathan Scales, Xinying Song, Xinyun Chen, Olivier Bousquet, and Denny Zhou. 2023. Compositional semantic parsing with large language models. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_33_2","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Dua Dheeru","year":"2022","unstructured":"Dheeru Dua, Shivanshu Gupta, Sameer Singh, and Matt Gardner. 2022. Successive prompting for decomposing complex questions. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Ali Edalati Marzieh Tahaei Ivan Kobyzev Vahid Partovi Nia James J. Clark and Mehdi Rezagholizadeh. 2025. KronA: Parameter-efficient tuning with kronecker adapter. In Enhancing LLM Performance: Efficacy Fine-Tuning and Inference Techniques. Cham: Springer Nature Switzerland 49\u201365.","DOI":"10.1007\/978-3-031-85747-8_4"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Mohammad Fahes Tuan-Hung Vu Andrei Bursuc Patrick P\u00e9rez and Raoul De Charette. 2023. Poda: Prompt-driven zero-shot domain adaptation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 18623\u201318633.","DOI":"10.1109\/ICCV51070.2023.01707"},{"key":"e_1_3_2_36_2","first-page":"6491","volume-title":"Proceedings of the 30th ACM SIGKDD Conference","author":"Fan Wenqi","year":"2024","unstructured":"Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. A survey on rag meeting llms: Towards retrieval-augmented large language models. In Proceedings of the 30th ACM SIGKDD Conference. 6491\u20136501."},{"key":"e_1_3_2_37_2","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Feng Yang","year":"2017","unstructured":"Yang Feng, Shiyue Zhang, Andi Zhang, Dong Wang, and Andrew Abel. 2017. Memory-augmented neural machine translation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_38_2","unstructured":"Luyu Gao Aman Madaan Shuyan Zhou Uri Alon Pengfei Liu Yiming Yang Jamie Callan and Graham Neubig. 2023. Pal: Program-aided language models. In International Conference on Machine Learning. PMLR 10764\u201310799."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","unstructured":"C. Ge et\u00a0al. 2022. Domain adaptation via prompt learning. In IEEE Transactions on Neural Networks and Learning Systems 36 1 (2022) 1160\u20131170. DOI:10.1109\/TNNLS.2023.3327962","DOI":"10.1109\/TNNLS.2023.3327962"},{"key":"e_1_3_2_40_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Grave Edouard","year":"2017","unstructured":"Edouard Grave, Armand Joulin, and Nicolas Usunier. 2017. Improving neural language models with a continuous cache. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_41_2","first-page":"8410","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Gu Yuxian","year":"2022","unstructured":"Yuxian Gu, Xu Han, Zhiyuan Liu, and Minlie Huang. 2022. PPT: Pre-trained prompt tuning for few-shot learning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Dublin, Ireland, 8410\u20138423."},{"key":"e_1_3_2_42_2","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","author":"Hambardzumyan Karen","year":"2021","unstructured":"Karen Hambardzumyan, Hrant Khachatrian, and Jonathan May. 2021. WARP: Word-level adversarial reprogramming. In Proceedings of the Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_43_2","unstructured":"Hangfeng He Hongming Zhang and Dan Roth. 2022. Rethinking with retrieval: Faithful large language model inference. arXiv:2301.00303. Retrieved from https:\/\/arxiv.org\/abs\/2301.00303"},{"key":"e_1_3_2_44_2","unstructured":"Junxian He Chunting Zhou Xuezhe Ma Taylor Berg-Kirkpatrick and Graham Neubig. 2022. Towards a unified view of parameter-efficient transfer learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Shwai He Liang Ding Daize Dong Jeremy Zhang and Dacheng Tao. 2022. SparseAdapter: An easy approach for improving the parameter-efficiency of adapters. In Findings of the Association for Computational Linguistics: EMNLP 2022. Association for Computational Linguistics 2184\u20132190.","DOI":"10.18653\/v1\/2022.findings-emnlp.160"},{"key":"e_1_3_2_46_2","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Bridging nonlinearities and stochastic regularizers with gaussian error linear Units. In International Conference on Learning Representations."},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Raghav Garg Mehul Manu Neha Chauhan Naveen Naval and C. Tharini. 2024. Manipulation and measurement of knowledge representations of language models. In 2024 2nd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS). IEEE 1249\u20131254.","DOI":"10.1109\/ICSSAS64001.2024.10760326"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Hou et\u00a0al. 2024. Large language models for software engineering: A systematic literature review. ACM TOSEM\u201924. 1\u201379.","DOI":"10.1145\/3695988"},{"key":"e_1_3_2_49_2","first-page":"2790","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In Proceedings of the International Conference on Machine Learning. PMLR, 2790\u20132799."},{"key":"e_1_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Howard Jeremy and Sebastian Ruder. 2018. Universal language model fine-tuning for text classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 328\u2013339.","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Cheng-Yu Hsieh Chun-Liang Li Chih-Kuan Yeh Hootan Nakhost Yasuhisa Fujii Alex Ratner Ranjay Krishna Chen-Yu Lee and Tomas Pfister. 2023. Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. In Findings of the Association for Computational Linguistics: ACL 2023. 8003\u20138017.","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"e_1_3_2_52_2","unstructured":"Edward Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations. 2022."},{"key":"e_1_3_2_53_2","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","author":"Hu Shengding","year":"2022","unstructured":"Shengding Hu, Ning Ding, Huadong Wang, Zhiyuan Liu, Jingang Wang, Juanzi Li, Wei Wu, and Maosong Sun. 2022. Knowledgeable prompt-tuning: Incorporating knowledge into prompt verbalizer for text classification. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Yuntong Hu Zhihan Lei Zheng Zhang Bo Pan Chen Ling and Liang Zhao. 2025. GRAG: Graph retrieval-augmented generation. In Findings of the Association for Computational Linguistics: NAACL 2025. 4145\u20134157.","DOI":"10.18653\/v1\/2025.findings-naacl.232"},{"key":"e_1_3_2_55_2","unstructured":"Zhiqiang Hu Lei Wang Yihuai Lan Wanyu Xu Ee-Peng Lim Lidong Bing Xing Xu Soujanya Poria and Roy Lee. 2023. LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 5254\u20135276."},{"key":"e_1_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Jiaxin Huang Shixiang Gu Le Hou Yuexin Wu Xuezhi Wang Hongkun Yu and Jiawei Han. 2023. Large language models can self-improve. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 1051\u20131068.","DOI":"10.18653\/v1\/2023.emnlp-main.67"},{"key":"e_1_3_2_57_2","unstructured":"Shaohan Huang Li Dong Wenhui Wang Yaru Hao Saksham Singhal Shuming Ma Tengchao Lv et\u00a0al. 2023. Language is not all you need: Aligning perception with language models. Advances in Neural Information Processing Systems 36 (2023) 72096\u201372109."},{"key":"e_1_3_2_58_2","unstructured":"Gautier Izacard Patrick Lewis Maria Lomeli Lucas Hosseini Fabio Petroni Timo Schick Jane Dwivedi-Yu Armand Joulin Sebastian Riedel and Edouard Grave. 2023. Atlas: Few-shot learning with retrieval augmented language models. J. Mach. Learn. Res. 24 1 Article 251 (January 2023)."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","unstructured":"K. Jeblick B. Schachtner J. Dexl A. Mittermeier A. T. St\u00fcber J. Topalis T. Weber P. Wesp B. O. Sabel J. Ricke and M. Ingrisch. 2022. ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports. Eur Radiol. 34 5 (2022) 2817\u20132825. DOI:10.1007\/s00330-023-10213-1","DOI":"10.1007\/s00330-023-10213-1"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_61_2","first-page":"10147","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Jia Chen","year":"2022","unstructured":"Chen Jia and Yue Zhang. 2022. Prompt-based distribution alignment for domain generalization in text classification. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 10147\u201310157."},{"key":"e_1_3_2_62_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Jiang Albert Qiaochu","year":"2023","unstructured":"Albert Qiaochu Jiang, Sean Welleck, Jin Peng Zhou, Timothee Lacroix, Jiacheng Liu, Wenda Li, Mateja Jamnik, Guillaume Lample, and Yuhuai Wu. 2023. Draft, sketch, and prove: Guiding formal theorem provers with informal proofs. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_63_2","doi-asserted-by":"crossref","unstructured":"Haoming Jiang Pengcheng He Weizhu Chen Xiaodong Liu Jianfeng Gao and Tuo Zhao. 2020. SMART: Robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2177\u20132190.","DOI":"10.18653\/v1\/2020.acl-main.197"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604613"},{"key":"e_1_3_2_65_2","article-title":"GeneGPT: Augmenting large language models with domain tools for improved access to biomedical information","author":"Jin Qiao","unstructured":"Qiao Jin, Yifan Yang, Qingyu Chen, and Zhiyong Lu. GeneGPT: Augmenting large language models with domain tools for improved access to biomedical information. ArXiv (n.d.).","journal-title":"ArXiv"},{"key":"e_1_3_2_66_2","article-title":"Scaling laws for neural language models","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv (2020).","journal-title":"arXiv"},{"key":"e_1_3_2_67_2","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume":"34","author":"Mahabadi Rabeeh Karimi","year":"2021","unstructured":"Rabeeh Karimi Mahabadi, James Henderson, and Sebastian Ruder. 2021. Compacter: Efficient low-rank hypercomplex adapter layers. Advances in Neural Information Processing Systems 34 (2021), 1022\u20131035.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_68_2","unstructured":"Urvashi Khandelwal Omer Levy Dan Jurafsky Luke Zettlemoyer and Mike Lewis. 2020. Generalization through memorization: Nearest neighbor language models. In International Conference on Learning Representations."},{"key":"e_1_3_2_69_2","unstructured":"Tushar Khot Harsh Trivedi Matthew Finlayson Yao Fu Kyle Richardson Peter Clark and Ashish Sabharwal. 2023. Decomposed prompting: A modular approach for solving complex tasks. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634966"},{"key":"e_1_3_2_71_2","volume-title":"Proceedings of the ICML 2022 Workshop on Knowledge Retrieval and Language Models","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. In Proceedings of the ICML 2022 Workshop on Knowledge Retrieval and Language Models."},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.579"},{"key":"e_1_3_2_73_2","first-page":"1087","article-title":"Are language models more like libraries or like librarians? Bibliotechnism, the novel reference problem, and the attitudes of LLMs","volume":"12","author":"Lederman Harvey","year":"2024","unstructured":"Harvey Lederman and Kyle Mahowald. 2024. Are language models more like libraries or like librarians? Bibliotechnism, the novel reference problem, and the attitudes of LLMs. Transactions of the Association for Computational Linguistics 12 (2024), 1087\u20131103.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"e_1_3_2_74_2","unstructured":"Eric Lehman Evan Hernandez Diwakar Mahajan Jonas Wulff Micah J. Smith Zachary Ziegler Daniel Nadler Peter Szolovits Alistair Johnson and Emily Alsentzer. 2023. Do we still need clinical language models? In Conference on Health Inference and Learning. PMLR 578\u2013597."},{"key":"e_1_3_2_75_2","doi-asserted-by":"crossref","unstructured":"Markus Leippold. 2023. Sentiment spin: Attacking financial sentiment with GPT-3. Finance Research Letters 55 PB (2023).","DOI":"10.1016\/j.frl.2023.103957"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_77_2","unstructured":"Yoav Levine Itay Dalmedigos Ori Ram Yoel Zeldes Daniel Jannai Dor Muhlgay Yoni Osin Opher Lieber Barak Lenz Shai Shalev-Shwartz et\u00a0al. 2022. Standing on the shoulders of giant frozen language models. arXiv:2204.10019. Retrieved from https:\/\/arxiv.org\/abs\/2204.10019"},{"key":"e_1_3_2_78_2","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et\u00a0al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459\u20139474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_79_2","doi-asserted-by":"crossref","unstructured":"Daliang Li Ankit Singh Rawat Manzil Zaheer Xin Wang Michal Lukasik Andreas Veit Felix Yu and Sanjiv Kumar. 2023. Large language models with controllable working memory. In Findings of the Association for Computational Linguistics: ACL 2023. 1774\u20131793.","DOI":"10.18653\/v1\/2023.findings-acl.112"},{"key":"e_1_3_2_80_2","unstructured":"Guohao Li Hasan Hammoud Hani Itani Dmitrii Khizbullin and Bernard Ghanem. 2023. Camel: Communicative agents for \u201cMind\u201d exploration of large language model society. Advances in Neural Information Processing Systems 36 (2023) 51991\u201352008."},{"key":"e_1_3_2_81_2","volume-title":"Proceedings of the International Conference on Computational Linguistics","author":"Li Haochen","year":"2022","unstructured":"Haochen Li, Tong Mo, Hongcheng Fan, Jingkun Wang, Jiaxi Wang, Fuhao Zhang, and Weiping Li. 2022. KiPT: Knowledge-injected prompt tuning for event detection. In Proceedings of the International Conference on Computational Linguistics."},{"key":"e_1_3_2_82_2","unstructured":"Jinyang Li Binyuan Hui Ge Qu Jiaxi Yang Binhua Li Bowen Li Bailin Wang et\u00a0al. 2023. Can llm already serve as a database interface? A big bench for large-scale database grounded text-to-SQLs. Advances in Neural Information Processing Systems 36 (2023) 42330\u201342357."},{"key":"e_1_3_2_83_2","article-title":"Prefix-Tuning: Optimizing continuous prompts for generation","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-Tuning: Optimizing continuous prompts for generation. In Proceedings of the 59th ACL.","journal-title":"In Proceedings of the 59th ACL."},{"key":"e_1_3_2_84_2","volume-title":"Proceedings of the Workshop on Language and Robotics at CoRL 2022","author":"Liang Jacky","year":"2022","unstructured":"Jacky Liang, Wenlong Huang, Fei Xia, Peng Xu, Karol Hausman, Pete Florence, and Andy Zeng. 2022. Code as policies: Language model programs for embodied control. In Proceedings of the Workshop on Language and Robotics at CoRL 2022."},{"key":"e_1_3_2_85_2","doi-asserted-by":"crossref","unstructured":"Yaobo Liang Chenfei Wu Ting Song Wenshan Wu Yan Xia Yu Liu Yang Ou et\u00a0al. 2024. Taskmatrix. AI: Completing tasks by connecting foundation models with millions of apis. Intelligent Computing 3 (2024) 0063.","DOI":"10.34133\/icomputing.0063"},{"key":"e_1_3_2_86_2","doi-asserted-by":"crossref","unstructured":"Hongzhan Lin Pengyao Yi Jing Ma Haiyun Jiang Ziyang Luo Shuming Shi and Ruifang Liu. 2023. Zero-shot rumor detection with propagation structure via prompt learning. In Proceedings of the AAAI Conference on Artificial Intelligence 37 4 (2023) 5213\u20135221.","DOI":"10.1609\/aaai.v37i4.25651"},{"key":"e_1_3_2_87_2","first-page":"8035","volume-title":"Findings of EMNLP","author":"Ling Chen","year":"2023","unstructured":"Chen Ling, Xuchao Zhang, Xujiang Zhao, Yanchi Liu, Wei Cheng, Mika Oishi, Takao Osaki, Katsushi Matsuda, Haifeng Chen, and Liang Zhao. 2023. Open-ended commonsense reasoning with unrestricted answer candidates. In Findings of EMNLP. 8035\u20138047."},{"key":"e_1_3_2_88_2","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume":"35","author":"Liu Haokun","year":"2022","unstructured":"Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin A. Raffel. 2022. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Advances in Neural Information Processing Systems 35 (2022), 1950\u20131965.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00476"},{"key":"e_1_3_2_91_2","unstructured":"Ruibo Liu Jason Wei Shixiang Shane Gu Te-Yen Wu Soroush Vosoughi Claire Cui Denny Zhou and Andrew M. Dai. 2023. Mind\u2019s Eye: Grounded language model reasoning through simulation. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_92_2","doi-asserted-by":"crossref","unstructured":"Xiao Liu Kaixuan Ji Yicheng Fu Weng Tam Zhengxiao Du Zhilin Yang and Jie Tang. 2022. P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 61\u201368.","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_3_2_93_2","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2022","author":"Liu Xiangyang","year":"2022","unstructured":"Xiangyang Liu, Tianxiang Sun, Xuanjing Huang, and Xipeng Qiu. 2022. Late prompt tuning: A late prompt could be better than many prompts. In Findings of the Association for Computational Linguistics: EMNLP 2022. Abu Dhabi, UAE."},{"key":"e_1_3_2_94_2","doi-asserted-by":"crossref","unstructured":"Yiheng Liu Tianle Han Siyuan Ma Jiayue Zhang Yuanyuan Yang Jiaming Tian Hao He et\u00a0al. 2023. Summary of chatgpt-related research and perspective towards the future of large language models. Meta-Radiology 1 2 (2023) 100017.","DOI":"10.1016\/j.metrad.2023.100017"},{"key":"e_1_3_2_95_2","doi-asserted-by":"crossref","unstructured":"Alejandro Lopez-Lira and Yuehua Tang. 2023. Can ChatGPT forecast stock price movements? return predictability and large language models. arXiv:2304.07619. Retrieved from https:\/\/arxiv.org\/abs\/2304.07619","DOI":"10.2139\/ssrn.4412788"},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591997"},{"key":"e_1_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"e_1_3_2_98_2","article-title":"ChatGPT and generative AI systems as quasi-expert legal advice lawyers-case study considering potential appeal against conviction of tom hayes","author":"Macey-Dare Rupert","year":"2023","unstructured":"Rupert Macey-Dare. 2023. ChatGPT and generative AI systems as quasi-expert legal advice lawyers-case study considering potential appeal against conviction of tom hayes. Available at SSRN 4342686 (2023), 35.","journal-title":"Available at SSRN 4342686"},{"key":"e_1_3_2_99_2","doi-asserted-by":"crossref","unstructured":"Aman Madaan Shuyan Zhou Uri Alon Yiming Yang and Graham Neubig. 2022. Language models of code are few-shot commonsense learners. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 1384\u20131403.","DOI":"10.18653\/v1\/2022.emnlp-main.90"},{"key":"e_1_3_2_100_2","doi-asserted-by":"publisher","unstructured":"B. Mahjour J. Hoffstadt and T. Cernak. 2023. Designing chemical reaction arrays using phactor and ChatGPT. Organic Process Research & Development 27 8 (2023) 1510\u20131516. 10.1021\/acs.oprd.3c00186","DOI":"10.1021\/acs.oprd.3c00186"},{"key":"e_1_3_2_101_2","doi-asserted-by":"crossref","unstructured":"Bhavitvya Malik Abhinav Ramesh Kashyap Min-Yen Kan and Soujanya Poria. 2023. UDAPTER-efficient domain adaptation using adapters. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2249\u20132263.","DOI":"10.18653\/v1\/2023.eacl-main.165"},{"key":"e_1_3_2_102_2","doi-asserted-by":"crossref","unstructured":"Yuning Mao Lambert Mathias Rui Hou Amjad Almahairi Hao Ma Jiawei Han Scott Yih and Madian Khabsa. 2022. UniPELT: A unified framework for parameter-efficient language model tuning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 6253\u20136264.","DOI":"10.18653\/v1\/2022.acl-long.433"},{"key":"e_1_3_2_103_2","unstructured":"Raja Marjieh Ilia Sucholutsky Pol van Rijn Nori Jacoby and Tom Griffiths. 2023. What language reveals about perception: Distilling psychophysical knowledge from large language models. In Proceedings of the Annual Meeting of the Cognitive Science Society 45 45 (2023)."},{"key":"e_1_3_2_104_2","first-page":"17359","article-title":"Locating and editing factual associations in gpt","volume":"35","author":"Meng Kevin","year":"2022","unstructured":"Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in gpt. Advances in Neural Information Processing Systems 35 (2022), 17359\u201317372.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_105_2","unstructured":"Kevin Meng Arnab Sen Sharma Alex J. Andonian Yonatan Belinkov and David Bau. 2022. Mass-editing memory in a transformer. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_106_2","unstructured":"Jacob Menick Maja Trebacz Vladimir Mikulik John Aslanides Francis Song Martin Chadwick Mia Glaese Susannah Young Lucy Campbell-Gillingham Geoffrey Irving et\u00a0al. 2022. Teaching language models to support answers with verified quotes. arXiv:2203.11147. Retrieved from https:\/\/arxiv.org\/abs\/2203.11147"},{"key":"e_1_3_2_107_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Merity Stephen","year":"2016","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. Pointer sentinel mixture models. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_108_2","unstructured":"Gr\u00e9goire Mialon Roberto Dessi Maria Lomeli Christoforos Nalmpantis Ramakanth Pasunuru Roberta Raileanu Baptiste Roziere et\u00a0al. 2023. Augmented language models: A survey. Transactions on Machine Learning Research. 2835\u20138856."},{"key":"e_1_3_2_109_2","doi-asserted-by":"crossref","unstructured":"Bonan Min Hayley Ross Elior Sulem Amir Pouran Ben Veyseh Thien Huu Nguyen Oscar Sainz Eneko Agirre Ilana Heintz and Dan Roth. 2023. Recent advances in natural language processing via large pre-trained language models: A survey. ACM Computing Surveys 56 2 (2023) 1\u201340.","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_110_2","doi-asserted-by":"crossref","unstructured":"Sewon Min Xinxi Lyu Ari Holtzman Mikel Artetxe Mike Lewis Hannaneh Hajishirzi and Luke Zettlemoyer. 2022. Rethinking the role of demonstrations: What makes in-context learning work? arXiv:2202.12837. Retrieved from https:\/\/arxiv.org\/abs\/2202.12837","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"e_1_3_2_111_2","unstructured":"Eric Mitchell Charles Lin Antoine Bosselut Chelsea Finn and Christopher D. Manning. 2022. Fast model editing at scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_112_2","first-page":"15817","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Mitchell Eric","year":"2022","unstructured":"Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D. Manning, and Chelsea Finn. 2022. Memory-based model editing at scale. In Proceedings of the International Conference on Machine Learning. 15817\u201315831."},{"key":"e_1_3_2_113_2","first-page":"zvad022\u2013zvad022","article-title":"ChatGPT: Can artificial intelligence language models be of value for cardiovascular nurses and allied health professionals.","author":"Moons Philip","year":"2023","unstructured":"Philip Moons and Liesbet Van Bulck. 2023. ChatGPT: Can artificial intelligence language models be of value for cardiovascular nurses and allied health professionals. European Journal of Cardiovascular Nursing 22, 7 (2023), zvad022\u2013zvad022.","journal-title":"European Journal of Cardiovascular Nursing"},{"key":"e_1_3_2_114_2","volume-title":"Proceedings of the NeurIPS Efficient Natural Language and Speech Processing Workshop","author":"Muhamed Aashiq","year":"2021","unstructured":"Aashiq Muhamed, Iman Keivanloo, Sujan Perera, James Mracek, Yi Xu, Qingjun Cui, Santosh Rajagopalan, Belinda Zeng, and Trishul Chilimbi. 2021. CTR-BERT: Cost-effective knowledge distillation for billion-parameter teacher models. In Proceedings of the NeurIPS Efficient Natural Language and Speech Processing Workshop."},{"key":"e_1_3_2_115_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3585602"},{"key":"e_1_3_2_116_2","unstructured":"Reiichiro Nakano Jacob Hilton Suchir Balaji Jeff Wu Long Ouyang Christina Kim Christopher Hesse Shantanu Jain Vineet Kosaraju William Saunders et\u00a0al. 2021. Webgpt: Browser-assisted question-answering with human feedback. arXiv:2112.09332. Retrieved from https:\/\/arxiv.org\/abs\/2112.09332"},{"key":"e_1_3_2_117_2","doi-asserted-by":"publisher","unstructured":"P. Niszczota and S. Abbas. 2023. GPT has become financially literate: Insights from financial literacy tests of GPT and a preliminary test of how people use it as a source of advice. SSRN Working Paper Abstract ID 4384861. 10.2139\/ssrn.4384861","DOI":"10.2139\/ssrn.4384861"},{"key":"e_1_3_2_118_2","article-title":"ChatGPT plugins","unstructured":"OpenAI. ChatGPT plugins. Retrieved from https:\/\/openai.com\/blog\/chatgpt-pluginsAccessed: 2023-04-05.","journal-title":"https:\/\/openai.com\/blog\/chatgpt-plugins"},{"key":"e_1_3_2_119_2","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_120_2","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et\u00a0al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730\u201327744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_121_2","doi-asserted-by":"crossref","unstructured":"Joon Sung Park Joseph O\u2019Brien Carrie Jun Cai Meredith Ringel Morris Percy Liang and Michael S. Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual Acm Symposium on User Interface Software and Technology. 1\u201322.","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_2_122_2","unstructured":"Baolin Peng Michel Galley Pengcheng He Hao Cheng Yujia Xie Yu Hu Qiuyuan Huang Lars Liden Zhou Yu Weizhu Chen et\u00a0al. 2023. Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv:2302.12813. Retrieved from https:\/\/arxiv.org\/abs\/2302.12813"},{"key":"e_1_3_2_123_2","unstructured":"Baolin Peng Chunyuan Li Pengcheng He Michel Galley and Jianfeng Gao. 2023. Instruction tuning with gpt-4. arXiv:2304.03277. Retrieved from https:\/\/arxiv.org\/abs\/2304.03277"},{"key":"e_1_3_2_124_2","doi-asserted-by":"crossref","unstructured":"Jonas Pfeiffer Aishwarya Kamath Andreas R\u00fcckl\u00e9 Kyunghyun Cho and Iryna Gurevych. 2021. AdapterFusion: Non-destructive task composition for transfer learning. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 487\u2013503.","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"e_1_3_2_125_2","doi-asserted-by":"crossref","unstructured":"Jonas Pfeiffer Andreas R\u00fcckl\u00e9 Clifton Poth Aishwarya Kamath Ivan Vuli\u0107 Sebastian Ruder Kyunghyun Cho and Iryna Gurevych. 2020. AdapterHub: A framework for adapting transformers. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 46\u201354.","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"e_1_3_2_126_2","doi-asserted-by":"crossref","unstructured":"Jonas Pfeiffer Ivan Vuli\u0107 Iryna Gurevych and Sebastian Ruder. 2020. MAD-X: An adapter-based framework for multi-task cross-lingual transfer. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 7654\u20137673.","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"e_1_3_2_127_2","doi-asserted-by":"crossref","first-page":"24","DOI":"10.18653\/v1\/2024.conll-1.3","volume-title":"Proceedings of the 28th Conference on Computational Natural Language Learning","author":"Pham Viet","year":"2024","unstructured":"Viet Pham, Shilin Qu, Farhad Moghimifar, Suraj Sharma, Yuan-Fang Li, Weiqing Wang, and Reza Haf. 2024. Multi-cultural norm base: Frame-based norm discovery in multi-cultural settings. In Proceedings of the 28th Conference on Computational Natural Language Learning. 24\u201335."},{"key":"e_1_3_2_128_2","first-page":"4346","volume-title":"Findings of EMNLP 2024","author":"Arco Flor Plaza-del","year":"2024","unstructured":"Flor Plaza-del Arco, Amanda Curry, Susanna Paoli, Alba Cercas Curry, and Dirk Hovy. 2024. Divine LLaMAs: Bias, stereotypes, stigmatization, and emotion representation of religion in large language models. In Findings of EMNLP 2024. 4346\u20134366."},{"key":"e_1_3_2_129_2","doi-asserted-by":"crossref","unstructured":"Edoardo Maria Ponti Alessandro Sordoni Yoshua Bengio and Siva Reddy. 2023. Combining parameter-efficient modules for task-level generalisation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 687\u2013702.","DOI":"10.18653\/v1\/2023.eacl-main.49"},{"key":"e_1_3_2_130_2","unstructured":"Mohammadreza Pourreza and Davood Rafiei. 2023. DIN-SQL: Decomposed in-context learning of text-to-SQL with self-correction. Advances in Neural Information Processing Systems 36 (2023) 36339\u201336348."},{"key":"e_1_3_2_131_2","first-page":"4","volume-title":"Proceedings of the CIRCLE (Joint Conference of the Information Retrieval Communities in Europe), Samatan, Gers, France","author":"Prasad Nishchal","year":"2022","unstructured":"Nishchal Prasad, Mohand Boughanem, and Taoufiq Dkaki. 2022. Effect of hierarchical domain-specific language models and attention in the classification of decisions for legal cases. In Proceedings of the CIRCLE (Joint Conference of the Information Retrieval Communities in Europe), Samatan, Gers, France. 4\u20137."},{"key":"e_1_3_2_132_2","unstructured":"Chengwei Qin and Shafiq Joty. 2022. LFPT5: A unified framework for lifelong few-shot language learning based on prompt tuning of T5. In International Conference on Learning Representations."},{"key":"e_1_3_2_133_2","doi-asserted-by":"crossref","unstructured":"Yujia Qin Shengding Hu Yankai Lin Weize Chen Ning Ding Ganqu Cui Zheni Zeng et\u00a0al. 2024. Tool learning with foundation models. ACM Computing Surveys 57 4 (2024) 1\u201340.","DOI":"10.1145\/3704435"},{"key":"e_1_3_2_134_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"e_1_3_2_135_2","unstructured":"A. Radford K. Narasimhan T. Salimans and I. Sutskever. 2018. Improving language understanding by generative pre-training. OpenAI Technical Report. Available at: https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf"},{"key":"e_1_3_2_136_2","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_137_2","doi-asserted-by":"crossref","unstructured":"Ori Ram Yoav Levine Itay Dalmedigos Dor Muhlgay Amnon Shashua Kevin Leyton-Brown and Yoav Shoham. 2023. In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics 11 (2023) 1316\u20131331.","DOI":"10.1162\/tacl_a_00605"},{"key":"e_1_3_2_138_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Razdaibiedina Anastasia","year":"2023","unstructured":"Anastasia Razdaibiedina, Yuning Mao, Rui Hou, Madian Khabsa, Mike Lewis, and Amjad Almahairi. 2023. Progressive prompts: Continual learning for language models. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_139_2","article-title":"Learning multiple visual domains with residual adapters","volume":"30","author":"Rebuffi Sylvestre-Alvise","year":"2017","unstructured":"Sylvestre-Alvise Rebuffi, Hakan Bilen, and Andrea Vedaldi. 2017. Learning multiple visual domains with residual adapters. Advances in Neural Information Processing Systems 30 (2017), 506\u2013516.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_140_2","doi-asserted-by":"crossref","unstructured":"Benjamin Reichman and Larry Heck. 2024. Dense passage retrieval: Is it Retrieving? In Findings of the Association for Computational Linguistics: EMNLP 2024. 13540\u201313553.","DOI":"10.18653\/v1\/2024.findings-emnlp.791"},{"key":"e_1_3_2_141_2","doi-asserted-by":"crossref","unstructured":"Adam Roberts Colin Raffel and Noam Shazeer. 2020. How much knowledge can you pack into the parameters of a language model? In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 5418\u20135426.","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"e_1_3_2_142_2","unstructured":"Joshua Robinson Christopher Rytting and David Wingate. 2023. Leveraging large language models for multiple choice question answering. In International Conference on Learning Representations."},{"key":"e_1_3_2_143_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00580-7"},{"key":"e_1_3_2_144_2","article-title":"The utility of ChatGPT as an example of large language models in healthcare education, research and practice: Systematic review on the future perspectives and potential limitations","author":"Sallam Malik","year":"2023","unstructured":"Malik Sallam. 2023. The utility of ChatGPT as an example of large language models in healthcare education, research and practice: Systematic review on the future perspectives and potential limitations. medRxiv (2023), 2023\u201302.","journal-title":"medRxiv"},{"key":"e_1_3_2_145_2","volume-title":"Proceedings of the ICLR","author":"Sanh Victor","year":"2022","unstructured":"Victor Sanh, Albert Webson, Colin Raffel, Stephen 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 Proceedings of the ICLR."},{"key":"e_1_3_2_146_2","unstructured":"Timo Schick Jane Dwivedi-Yu Roberto Dess\u00ec Roberta Raileanu Maria Lomeli Eric Hambro Luke Zettlemoyer Nicola Cancedda and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems 36 (2023) 68539\u201368551."},{"key":"e_1_3_2_147_2","doi-asserted-by":"crossref","unstructured":"Timo Schick and Hinrich Sch\u00fctze. 2021. Exploiting cloze-questions for few-shot text classification and natural language inference. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 255\u2013269.","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"e_1_3_2_148_2","unstructured":"Dale Schuurmans. 2023. Memory augmented large language models are computationally universal. arXiv:2301.04589. Retrieved from https:\/\/arxiv.org\/abs\/2301.04589"},{"key":"e_1_3_2_149_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.410"},{"key":"e_1_3_2_150_2","first-page":"2139","volume-title":"Proceedings of the 2020 IEEE International Conference on Big Data","author":"Shaghaghian Shohreh","year":"2020","unstructured":"Shohreh Shaghaghian, Luna Yue Feng, Borna Jafarpour, and Nicolai Pogrebnyakov. 2020. Customizing contextualized language models for legal document reviews. In Proceedings of the 2020 IEEE International Conference on Big Data. 2139\u20132148."},{"key":"e_1_3_2_151_2","unstructured":"Yongliang Shen Kaitao Song Xu Tan Dongsheng Li Weiming Lu and Yueting Zhuang. 2023. HuggingGPT: Solving AI tasks with ChatGPT and its friends in hugging face. Advances in Neural Information Processing Systems 36 (2023) 38154\u201338180."},{"key":"e_1_3_2_152_2","article-title":"Continual learning with deep generative replay","volume":"30","author":"Shin Hanul","year":"2017","unstructured":"Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. 2017. Continual learning with deep generative replay. Advances in Neural Information Processing Systems 30 (2017), 2990\u20132999.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_153_2","doi-asserted-by":"crossref","unstructured":"Kumar Shridhar Alessandro Stolfo and Mrinmaya Sachan. 2023. Distilling reasoning capabilities into smaller language models. In Findings of the Association for Computational Linguistics: ACL 2023. 7059\u20137073.","DOI":"10.18653\/v1\/2023.findings-acl.441"},{"key":"e_1_3_2_154_2","first-page":"25968","article-title":"End-to-end training of multi-document reader and retriever for open-domain question answering","volume":"34","author":"Singh Devendra","year":"2021","unstructured":"Devendra Singh, Siva Reddy, Will Hamilton, Chris Dyer, and Dani Yogatama. 2021. End-to-end training of multi-document reader and retriever for open-domain question answering. Advances in Neural Information Processing Systems 34 (2021), 25968\u201325981.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_155_2","volume-title":"Proceedings of the Workshop on Language and Robotics at CoRL 2022","author":"Singh Ishika","unstructured":"Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, and Animesh Garg. ProgPrompt: Generating situated robot task plans using large language models. In Proceedings of the Workshop on Language and Robotics at CoRL 2022."},{"key":"e_1_3_2_156_2","doi-asserted-by":"crossref","unstructured":"Weihang Su Yichen Tang Qingyao Ai Zhijing Wu and Yiqun Liu. 2024. DRAGIN: Dynamic retrieval augmented generation based on the real-time information needs of large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 12991\u201313013.","DOI":"10.18653\/v1\/2024.acl-long.702"},{"key":"e_1_3_2_157_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.290"},{"key":"e_1_3_2_158_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Sun Tianxiang","year":"2022","unstructured":"Tianxiang Sun, Yunfan Shao, Hong Qian, Xuanjing Huang, and Xipeng Qiu. 2022. Black-Box tuning for language-model-as-a-service. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_3_2_159_2","first-page":"12991","article-title":"Lst: Ladder side-tuning for parameter and memory efficient transfer learning","volume":"35","author":"Sung Yi-Lin","year":"2022","unstructured":"Yi-Lin Sung, Jaemin Cho, and Mohit Bansal. 2022. Lst: Ladder side-tuning for parameter and memory efficient transfer learning. Advances in Neural Information Processing Systems 35 (2022), 12991\u201313005.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_160_2","doi-asserted-by":"crossref","unstructured":"D\u00eddac Sur\u00eds Sachit Menon and Carl Vondrick. 2023. Vipergpt: Visual inference via Python execution for reasoning. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 11888\u201311898.","DOI":"10.1109\/ICCV51070.2023.01092"},{"issue":"9","key":"e_1_3_2_161_2","doi-asserted-by":"crossref","first-page":"page 346","DOI":"10.1093\/pnasnexus\/pgae346","article-title":"Cultural bias and cultural alignment of large language models","volume":"3","author":"Tao Yan","year":"2024","unstructured":"Yan Tao, Olga Viberg, Ryan S. Baker, and Ren\u00e9 F. Kizilcec. 2024. Cultural bias and cultural alignment of large language models. PNAS Nexus 3, 9 (2024), page 346.","journal-title":"PNAS Nexus"},{"key":"e_1_3_2_162_2","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M. Dai Anja Hauth Katie Millican et\u00a0al. 2023. Gemini: A family of highly capable multimodal models. arXiv:2312.11805. Retrieved from https:\/\/arxiv.org\/abs\/2312.11805"},{"issue":"1","key":"e_1_3_2_163_2","doi-asserted-by":"crossref","first-page":"bbad493","DOI":"10.1093\/bib\/bbad493","article-title":"Opportunities and challenges for ChatGPT and large language models in biomedicine and health","volume":"25","author":"Tian Shubo","year":"2024","unstructured":"Shubo Tian, Qiao Jin, Lana Yeganova, Po-Ting Lai, Qingqing Zhu, Xiuying Chen, et\u00a0al. 2024. Opportunities and challenges for ChatGPT and large language models in biomedicine and health. Briefings in Bioinformatics 25, 1 (2024), bbad493.","journal-title":"Briefings in Bioinformatics"},{"key":"e_1_3_2_164_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv:2302.13971. Retrieved from https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_165_2","unstructured":"Dietrich Trautmann Alina Petrova and Frank Schilder. 2022. Legal prompt engineering for multilingual legal judgement prediction. arXiv:2212.02199. Retrieved from https:\/\/arxiv.org\/abs\/2212.02199"},{"key":"e_1_3_2_166_2","doi-asserted-by":"crossref","unstructured":"Mojtaba Valipour Mehdi Rezagholizadeh Ivan Kobyzev and Ali Ghodsi. 2023. DyLoRA: Parameter-efficient tuning of pre-trained models using dynamic search-free low-rank adaptation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 3274\u20133287.","DOI":"10.18653\/v1\/2023.eacl-main.239"},{"key":"e_1_3_2_167_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00532"},{"key":"e_1_3_2_168_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017), 5998\u20136008.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_169_2","doi-asserted-by":"crossref","unstructured":"Tu Vu Brian Lester Noah Constant Rami Al-Rfou and Daniel Cer. 2022. SPoT: Better frozen model adaptation through soft prompt transfer. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 5039\u20135059.","DOI":"10.18653\/v1\/2022.acl-long.346"},{"key":"e_1_3_2_170_2","unstructured":"Danilo Vucetic Mohammadreza Tayaranian Maryam Ziaeefard James J. Clark Brett H. Meyer and Warren J. Gross. 2022. Efficient fine-tuning of compressed language models with learners. ICML 2022 Workshop on Hardware-Aware Efficient Training (HAET 2022)."},{"key":"e_1_3_2_171_2","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Wan Zhongwei","year":"2022","unstructured":"Zhongwei Wan, Yichun Yin, Wei Zhang, Jiaxin Shi, Lifeng Shang, Guangyong Chen, Xin Jiang, and Qun Liu. 2022. G-MAP: General memory-augmented pre-trained language model for domain tasks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_172_2","doi-asserted-by":"crossref","unstructured":"Longyue Wang Chenyang Lyu Tianbo Ji Zhirui Zhang Dian Yu Shuming Shi and Zhaopeng Tu. 2023. Document-level machine translation with large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 16646\u201316661.","DOI":"10.18653\/v1\/2023.emnlp-main.1036"},{"key":"e_1_3_2_173_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Wang Ruijie","year":"2022","unstructured":"Ruijie Wang, Zheng Li, Dachun Sun, Shengzhong Liu, Jinning Li, Bing Yin, and Tarek Abdelzaher. 2022. Learning to sample and aggregate: Few-shot reasoning over temporal knowledge graphs. In Proceedings of the Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_174_2","doi-asserted-by":"crossref","unstructured":"Ruize Wang Duyu Tang Nan Duan Zhongyu Wei Xuan-Jing Huang Jianshu Ji Guihong Cao Daxin Jiang and Ming Zhou. 2021. K-adapter: Infusing knowledge into pre-trained models with adapters. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 1405\u20131418.","DOI":"10.18653\/v1\/2021.findings-acl.121"},{"key":"e_1_3_2_175_2","doi-asserted-by":"crossref","unstructured":"Sheng Wang Zihao Zhao Xi Ouyang Tianming Liu Qian Wang and Dinggang Shen. 2024. Interactive computer-aided diagnosis on medical image using large language models. Communications Engineering 3 1 (2024) 133.","DOI":"10.1038\/s44172-024-00271-8"},{"key":"e_1_3_2_176_2","unstructured":"Xuezhi Wang Jason Wei Dale Schuurmans Quoc Le Ed Chi and Denny Zhou. 2022. Rationale-augmented ensembles in language models. arXiv:2207.00747. Retrieved from https:\/\/arxiv.org\/abs\/2207.00747"},{"key":"e_1_3_2_177_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Wang Xuezhi","year":"2023","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-consistency improves chain of thought reasoning in language models. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_178_2","doi-asserted-by":"publisher","unstructured":"Y. Wang Y. Kordi S. Mishra A. Liu N. A. Smith D. Khashabi and H. Hajishirzi. 2023. Self-Instruct: Aligning language models with self-generated instructions. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023) Long Papers 13484\u201313508. 10.18653\/v1\/2023.acl-long.754","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"e_1_3_2_179_2","doi-asserted-by":"crossref","unstructured":"Yile Wang Peng Li Maosong Sun and Yang Liu. 2023. Self-knowledge guided retrieval augmentation for large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023. 10303\u201310315.","DOI":"10.18653\/v1\/2023.findings-emnlp.691"},{"key":"e_1_3_2_180_2","doi-asserted-by":"crossref","unstructured":"Yaqing Wang Subhabrata Mukherjee Xiaodong Liu Jing Gao Ahmed Hassan Awadallah and Jianfeng Gao. 2022. Adamix: Mixture-of-adapter for parameter-efficient tuning of large language models. arXiv:2205.12410. Retrieved from https:\/\/arxiv.org\/abs\/2205.12410","DOI":"10.18653\/v1\/2022.emnlp-main.388"},{"key":"e_1_3_2_181_2","unstructured":"Yihan Wang Si Si Daliang Li Michal Lukasik Felix Yu Cho-Jui Hsieh Inderjit S. Dhillon and Sanjiv Kumar. 2022. Preserving In-Context Learning ability in Large Language Model Fine-tuning. arXiv:2211.00635. Retrieved from https:\/\/arxiv.org\/abs\/2211.00635"},{"key":"e_1_3_2_182_2","unstructured":"Zihao Wang Shaofei Cai Guanzhou Chen Anji Liu Xiaojian Ma Yitao Liang and Team CraftJarvis. 2023. Describe explain plan and select: interactive planning with large language models enables open-world multi-task agents. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 34153\u201334189."},{"key":"e_1_3_2_183_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Wei Jason","year":"2022","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 Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_184_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 International Conference on Learning Representations."},{"key":"e_1_3_2_185_2","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama et\u00a0al. 2022. Emergent abilities of large language models. Transactions on Machine Learning Research. 2835\u20138856."},{"key":"e_1_3_2_186_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Proceedings of the Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_187_2","article-title":"ChatGPT Gets Its \u201cWolfram Superpowers\u201d!","author":"Wolfram Stephen","unstructured":"Stephen Wolfram. ChatGPT Gets Its \u201cWolfram Superpowers\u201d! Retrieved from https:\/\/writings.stephenwolfram.com\/2023\/03\/chat gpt-gets-its-wolfram-superpowers\/Accessed: 2023-03-27.","journal-title":"https:\/\/writings.stephenwolfram.com\/2023\/03\/chat gpt-gets-its-wolfram-superpowers\/"},{"key":"e_1_3_2_188_2","unstructured":"Shijie Wu Ozan Irsoy Steven Lu Vadim Dabravolski Mark Dredze Sebastian Gehrmann Prabhanjan Kambadur David Rosenberg and Gideon Mann. 2023. Bloomberggpt: A large language model for finance. arXiv:2303.17564. Retrieved from https:\/\/arxiv.org\/abs\/2303.17564"},{"key":"e_1_3_2_189_2","volume-title":"Proceedings of the North American Chapter of the Association for Computational Linguistics","author":"Wu Zhuofeng","year":"2022","unstructured":"Zhuofeng Wu, Sinong Wang, Jiatao Gu, Rui Hou, Yuxiao Dong, V. G. Vinod Vydiswaran, and Hao Ma. 2022. IDPG: An Instance-Dependent Prompt Generation Method. In Proceedings of the North American Chapter of the Association for Computational Linguistics."},{"key":"e_1_3_2_190_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Xiao Guangxuan","unstructured":"Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. Efficient Streaming Language Models with Attention Sinks. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_2_191_2","unstructured":"Runxin Xu Fuli Luo Zhiyuan Zhang Chuanqi Tan Baobao Chang Songfang Huang and Fei Huang. 2021. Raise a child in large language model: Towards effective and generalizable fine-tuning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 9514\u20139528."},{"key":"e_1_3_2_192_2","volume-title":"Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022","author":"Yang Jingfeng","year":"2022","unstructured":"Jingfeng Yang, Haoming Jiang, Qingyu Yin, Danqing Zhang, Bing Yin, and Diyi Yang. 2022. SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models. In Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022."},{"key":"e_1_3_2_193_2","article-title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","author":"Yang Jingfeng","year":"2023","unstructured":"Jingfeng Yang, Hongye Jin, Ruixiang Tang, Xiaotian Han, Qizhang Feng, Haoming Jiang, Bing Yin, and Xia Hu. 2023. Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond. arXiv (2023).","journal-title":"arXiv"},{"key":"e_1_3_2_194_2","doi-asserted-by":"crossref","unstructured":"Kai-Cheng Yang and Filippo Menczer. 2025. Accuracy and political bias of news source credibility ratings by large language models. In Proceedings of the 17th ACM Web Science Conference 2025. 127\u2013137.","DOI":"10.1145\/3717867.3717903"},{"key":"e_1_3_2_195_2","unstructured":"Xianjun Yang Wei Cheng Xujiang Zhao Linda Petzold and Haifeng Chen. 2023. Dynamic Prompting: A Unified Framework for Prompt Tuning. arXiv:2303.02909. Retrieved from https:\/\/arxiv.org\/abs\/2303.02909"},{"key":"e_1_3_2_196_2","unstructured":"Zonghan Yang Xiaoyuan Yi Peng Li Yang Liu and Xing Xie. 2023. Unified detoxifying and debiasing in language generation via inference-time adaptive optimization. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_197_2","doi-asserted-by":"crossref","unstructured":"Fuda Ye Shuangyin Li Yongqi Zhang and Lei Chen. 2024. R2AG: Incorporating retrieval information into retrieval augmented generation. In Findings of the Association for Computational Linguistics: EMNLP 2024. 11584\u201311596.","DOI":"10.18653\/v1\/2024.findings-emnlp.678"},{"key":"e_1_3_2_198_2","article-title":"Ontology-enhanced Prompt-tuning for Few-shot Learning","author":"Ye Hongbin","year":"2022","unstructured":"Hongbin Ye, Ningyu Zhang, Shumin Deng, Xiang Chen, Hui Chen, Feiyu Xiong, Xi Chen, and Huajun Chen. 2022. Ontology-enhanced Prompt-tuning for Few-shot Learning. In Proceedings of the ACM Web Conference 2022.","journal-title":"In Proceedings of the ACM Web Conference 2022."},{"key":"e_1_3_2_199_2","unstructured":"Fangyi Yu Lee Quartey and Frank Schilder. 2022. Legal Prompting: Teaching a Language Model to Think Like a Lawyer. arXiv:2212.01326. Retrieved from https:\/\/arxiv.org\/abs\/2212.01326"},{"key":"e_1_3_2_200_2","doi-asserted-by":"crossref","unstructured":"Elad Ben Zaken Yoav Goldberg and Shauli Ravfogel. 2022. BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 1\u20139.","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"e_1_3_2_201_2","unstructured":"Chaoning Zhang Chenshuang Zhang Sheng Zheng Yu Qiao Chenghao Li Mengchun Zhang Sumit Kumar Dam Chu Myaet Thwal Ye Lin Tun Le Luang Huy et\u00a0al. 2023. A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need? arXiv:2303.11717. Retrieved from https:\/\/arxiv.org\/abs\/2303.11717"},{"key":"e_1_3_2_202_2","unstructured":"Haojie Zhang Ge Li Jia Li Zhongjin Zhang Yuqi Zhu and Zhi Jin. 2022. Fine-tuning pre-trained language models effectively by optimizing subnetworks adaptively. Advances in Neural Information Processing Systems 35 (2022) 21442\u201321454."},{"key":"e_1_3_2_203_2","unstructured":"Renrui Zhang Jiaming Han Chris Liu Peng Gao Aojun Zhou Xiangfei Hu Shilin Yan Pan Lu Hongsheng Li and Yu Qiao. 2024. LLaMA-Adapter: Efficient fine-tuning of language models with zero-init attention. In The International Conference on Learning Representations."},{"key":"e_1_3_2_204_2","unstructured":"Rongsheng Zhang Yinhe Zheng Xiaoxi Mao and Minlie Huang. 2021. Unsupervised domain adaptation with adapter. In Efficient Natural Language and Speech Processing (Models Training and Inference) 35th Conference on Neural Information Processing Systems (NeurIPS 2021)."},{"key":"e_1_3_2_205_2","unstructured":"Zhuosheng Zhang Aston Zhang Mu Li and Alex Smola. 2023. Automatic chain of thought prompting in large language models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_206_2","doi-asserted-by":"crossref","unstructured":"Hongyu Zhao Hao Tan and Hongyuan Mei. 2022. Tiny-attention adapter: Contexts are more important than the number of parameters. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 6626\u20136638.","DOI":"10.18653\/v1\/2022.emnlp-main.444"},{"key":"e_1_3_2_207_2","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et\u00a0al. 2023. A Survey of Large Language Models. arXiv:2303.18223. Retrieved from https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"e_1_3_2_208_2","volume-title":"Proceedings of the ICLR","author":"Zhou Denny","year":"2023","unstructured":"Denny Zhou, Nathanael Sch\u00e4rli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc V. Le, and Ed H. Chi. 2023. Least-to-Most Prompting Enables Complex Reasoning in Large Language Models. In Proceedings of the ICLR."},{"key":"e_1_3_2_209_2","unstructured":"Han Zhou Xingchen Wan Lev Proleev Diana Mincu Jilin Chen Katherine A. Heller and Subhrajit Roy. 2024. Batch Calibration: Rethinking calibration for in-context learning and prompt engineering. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_210_2","doi-asserted-by":"crossref","unstructured":"Le Zhuo Zewen Chi Minghao Xu He-Yan Huang Jianan Zhao Heqi Zheng Conghui He Xian-Ling Mao and Wentao Zhang. 2024. ProtLLM: An interleaved protein-language LLM with protein-as-word pre-training. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 8950\u20138963.","DOI":"10.18653\/v1\/2024.acl-long.484"},{"key":"e_1_3_2_211_2","unstructured":"Daniel M. Ziegler Nisan Stiennon Jeffrey Wu Tom B. Brown Alec Radford Dario Amodei Paul Christiano and Geoffrey Irving. 2019. Fine-tuning language models from human preferences. arXiv:1909.08593. Retrieved from https:\/\/arxiv.org\/abs\/1909.08593"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3764579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T13:58:28Z","timestamp":1759759108000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3764579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":210,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,2,28]]}},"alternative-id":["10.1145\/3764579"],"URL":"https:\/\/doi.org\/10.1145\/3764579","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,6]]},"assertion":[{"value":"2023-07-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}