{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T14:32:10Z","timestamp":1765031530944,"version":"3.46.0"},"reference-count":293,"publisher":"Association for Computing Machinery (ACM)","issue":"6","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>Idea and hypothesis generation are creative processes that demand a significant level of reasoning. Methods such as brainstorming, analytical reasoning, inductive reasoning and other forms of reasoning have proven useful in advancing research in this domain. Machine learning techniques have been widely investigated to address these challenging tasks. However, they are limited and have insufficient reasoning required for these tasks, making the emergence of language models reignite research in this direction. Large language models (LLMs) have debuted as the current state-of-the-art for achieving impressive generative tasks, and to support language understanding. Models such as the BERT, BARD, GPT and LLaMa have architectural layouts which are mostly transformer network based. These models headline impressive results in downstream tasks such as text classification, sentiment analysis, language inference, question answering, text summarization and named entity recognition among others. However, the need to adapt these models to the emerging downstream tasks of idea and hypothesis generation have uncovered a new research opportunity. In this study, systematic literature review is carried out to provide understanding on how LLMs have been applied to the classical downstream tasks and to then motivate adaptation of LLMs to idea and hypothesis generation. Furthermore, the study examines techniques applied to customization and knowledge distillation with the aim of contextualizing these methods to solve idea and hypothesis generation. We then explored the limitations of LLM-based research efforts to idea and hypothesis generation. A detailed and technical discussion of the findings of the study is presented, and we provide a high-level novel conceptual framework to describe and summarize our findings. Also, potential insights to combining knowledge graphs, causal inference, logic reasoning and LLMs distillation in idea and hypothesis generation are discussed. Finally, challenges in these research areas on adaptation of LLMs to idea and hypothesis generation are discussed.<\/jats:p>","DOI":"10.1145\/3774628","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T11:16:38Z","timestamp":1762254998000},"page":"1-40","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Survey of Adaptation of Large Language Models to Idea and Hypothesis Generation: Downstream Task Adaptation, Knowledge Distillation Approaches and Challenges"],"prefix":"10.1145","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1252-0719","authenticated-orcid":false,"given":"Olaide N","family":"Oyelade","sequence":"first","affiliation":[{"name":"Department of Computer Systems and Technology, North Carolina A&T State University","place":["Greensboro, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2633-6015","authenticated-orcid":false,"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast","place":["Belfast, United Kingdom of Great Britain and Northern Ireland"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6889-8587","authenticated-orcid":false,"given":"Karen","family":"Rafferty","sequence":"additional","affiliation":[{"name":"Queen's University Belfast","place":["Belfast, United Kingdom of Great Britain and Northern Ireland"]}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016223"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-023-09930-z"},{"key":"e_1_3_2_4_2","article-title":"Artificial understanding: a step toward robust AI","author":"Firt E.","year":"2023","unstructured":"E. Firt. 2023. Artificial understanding: a step toward robust AI. AI and Society 39, 4 (2023), 1653--1665.","journal-title":"AI and Society"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.444"},{"key":"e_1_3_2_6_2","volume-title":"Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning","author":"Warstadt A.","year":"2023","unstructured":"A. Warstadt, A. Mueller, L. Choshen, E. Wilcox, C. Zhuang, J. Ciro, R. Mosquera, B. Paranjabe, A. Williams, and T. L. a. R. Cotterell. 2023. GPT-wee: How Small Can a Small Language Model Really Get? In Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.39"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.795"},{"key":"e_1_3_2_9_2","article-title":"Rethinking Knowledge Graph Evaluation Under the Open-World Assumption","author":"Yang H.","year":"2022","unstructured":"H. Yang, Z. Lin, and M. Zhang. 2022. Rethinking Knowledge Graph Evaluation Under the Open-World Assumption. In in Advances in Neural Information Processing Systems (NeurIPS 2022) 35 (2022).","journal-title":"in Advances in Neural Information Processing Systems (NeurIPS 2022)"},{"key":"e_1_3_2_10_2","article-title":"Biologically-Plausible determinant maximization neural networks for blind separation of correlated sources","author":"Bozkurt B.","year":"2022","unstructured":"B. Bozkurt, C. Pehlevan, and A. Erdogan. 2022. Biologically-Plausible determinant maximization neural networks for blind separation of correlated sources. In Advances in Neural Information Processing Systems (NeurIPS 2022) 35 (2022).","journal-title":"Advances in Neural Information Processing Systems (NeurIPS 2022)"},{"key":"e_1_3_2_11_2","article-title":"What Can Transformers Learn In-Context? A case study of simple function classes","author":"Garg S.","year":"2022","unstructured":"S. Garg, D. Tsipras, P. S. Liang, and G. Valiant. 2022. What Can Transformers Learn In-Context? A case study of simple function classes. In Advances in Neural Information Processing Systems (NeurIPS 2022) 35 (2022).","journal-title":"Advances in Neural Information Processing Systems (NeurIPS 2022)"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.189"},{"key":"e_1_3_2_13_2","article-title":"When to make exceptions: Exploring language models as accounts of human moral judgment","author":"Jin Z.","year":"2022","unstructured":"Z. Jin, S. Levine, F. G. Adauto, O. Kamal, M. Sap, M. Sachan, R. Mihalcea, J. Tenenbaum, and B. Sch\u00f6lkopf. 2022. When to make exceptions: Exploring language models as accounts of human moral judgment. In Advances in Neural Information Processing Systems (NeurIPS 2022) 35 (2022).","journal-title":"Advances in Neural Information Processing Systems (NeurIPS 2022)"},{"key":"e_1_3_2_14_2","article-title":"Molecule generation by principal subgraph mining and assembling","author":"Kong X.","year":"2022","unstructured":"X. Kong, W. Huang, Z. Tan, and Y. Liu. 2022. Molecule generation by principal subgraph mining and assembling. In Advances in Neural Information Processing Systems (NeurIPS 2022) 35 (2022).","journal-title":"Advances in Neural Information Processing Systems (NeurIPS 2022)"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.252"},{"key":"e_1_3_2_16_2","volume-title":"(NeurIPS 2022)","author":"Xu D.","year":"2022","unstructured":"D. Xu, S. Mukherjee, X. Liu, D. Dey, W. Wang, X. Zhang, A. H. Awadallah, and J. Gao. 2022. Few-shot task-agnostic neural architecture search for distilling large language models. In (NeurIPS 2022)."},{"key":"e_1_3_2_17_2","article-title":"Public wisdom matters! Discourse-Aware hyperbolic fourier Co-Attention for social text classification","author":"Grover K.","year":"2022","unstructured":"K. Grover, S. M. P. Angara, M. S. Akhtar, and T. Chakraborty. 2022. Public wisdom matters! Discourse-Aware hyperbolic fourier Co-Attention for social text classification. In Advances in Neural Information Processing Systems (NeurIPS 2022) 35 (2022).","journal-title":"Advances in Neural Information Processing Systems (NeurIPS 2022)"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.246"},{"key":"e_1_3_2_19_2","unstructured":"W. X. Zhao K. Zhou J. Li T. Tang X. Wang Y. Hou Y. Min B. Zhang J. Zhang Z. Dong Y. Du C. Yang Y. Chen Z. Chen J. Jiang R. Ren Y. Li X. Tang Z. Liu and P. Liu. 2023. A survey of large language models. arXiv:2303.18223. Retrieved from https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"e_1_3_2_20_2","volume-title":"arXiv:2402.13116v1 [cs.CL]","author":"Xu X.","year":"2024","unstructured":"X. Xu, M. Li, C. Tao, T. Shen, R. Cheng, and J. Li. 2024. A survey on knowledge distillation of large language models. arXiv:2402.13116v1 [cs.CL]."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_22_2","article-title":"Towards reasoning in large language models: A survey","author":"Huang J.","year":"2023","unstructured":"J. Huang and K. C.-C. Chang. 2023. Towards reasoning in large language models: A survey. ACL: Association for Computational Linguistics 6, 10 (2023), 10370.","journal-title":"ACL: Association for Computational Linguistics"},{"issue":"13","key":"e_1_3_2_23_2","article-title":"The debate over understanding in AI's large language models","volume":"120","author":"Mitchell M.","year":"2023","unstructured":"M. Mitchell and D. C. Krakauer. 2023. The debate over understanding in AI's large language models. PNAS- Perspective Computer Science 120, 13 (2023).","journal-title":"PNAS- Perspective Computer Science"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73103-8_53"},{"key":"e_1_3_2_27_2","volume-title":"ACL","author":"Chen B.","year":"2023","unstructured":"B. Chen, D. Zan, F. Zhang, D. Lu, B. Wu, B. Guan, Y. Wang, and J.-G. Lou. 2023. Large language models meet NL2Code: A survey. In ACL."},{"key":"e_1_3_2_28_2","volume-title":"TMLR","author":"Mialon G.","year":"2023","unstructured":"G. Mialon, R. Dessi, M. Lomeli, C. Nalmpantis, R. Pasunuru, R. Raileanu, B. Roziere, T. Schick, J. Dwivedi-Yu, A. Celikyilmaz, E. Grave, Y. LeCun, and T. Scialom. 2023. Augmented language models: A Survey. TMLR."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.technovation.2023.102883"},{"key":"e_1_3_2_30_2","unstructured":"A. Harzing. 2023. Publish or perish publish or perish. [Online]. Available: https:\/\/harzing.com\/resources\/publish-or-perish. [Accessed 23 8 2023]."},{"volume-title":"International AAAI Conference on Weblogs and Social Media","year":"2009","key":"e_1_3_2_31_2","unstructured":"B. M., H. S. and J. M. 2009. Gephi: An open source software for exploring and manipulating networks. In International AAAI Conference on Weblogs and Social Media."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_2_33_2","doi-asserted-by":"crossref","unstructured":"A. Wettig T. Gao Z. Zhong and D. Chen. 2022. Should You Mask 15% in Masked Language Modeling? arXiv:2202.08005 [cs.CL].","DOI":"10.18653\/v1\/2023.eacl-main.217"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cola.2023.101200"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1057\/s41599-024-03407-5"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.nlp4science-1.17"},{"key":"e_1_3_2_38_2","article-title":"ChatGPT: deconstructing the debate and moving it forward","author":"Coeckelbergh M.","year":"2023","unstructured":"M. Coeckelbergh and D. Gunkel. 2023. ChatGPT: deconstructing the debate and moving it forward. AI and Society 39, 5 (2023), 2221--2231.","journal-title":"AI and Society"},{"key":"e_1_3_2_39_2","unstructured":"Y. Fu H. Peng and T. Khot. 2023. How does GPT Obtain its Ability? Tracing Emergent Abilities of Language Models to their Sources. [Online]. Retrieved from https:\/\/yaofu.notion.site\/How-does-GPT-Obtain-its-Ability-Tracing-Emergent-Abilities-of-Language-Models-to-their-Sources-b9a57ac0fcf74f30a1ab9e3e36fa1dc1. [Accessed 2 8 2023]."},{"key":"e_1_3_2_40_2","article-title":"Are the BERT family zero-shot learners? A study on their potential and limitations","author":"Wang Y.","unstructured":"Y. Wang, L. Wu, J. Li, X. Liang, and M. Zhang. Are the BERT family zero-shot learners? A study on their potential and limitations. Artificial Intelligence 322, C.","journal-title":"Artificial Intelligence"},{"key":"e_1_3_2_41_2","unstructured":"H. Touvron T. Lavril G. Izacard X. Martinet M.-A. Lachaux T. Lacroix B. Rozi\u00e8re N. Goyal E. Hambro F. Azhar A. Rodriguez A. Joulin and E. Grave. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971 [cs.CL]."},{"key":"e_1_3_2_42_2","unstructured":"S. Rajbhandari J. Rasley O. Ruwase and Y. He. ZeRO: Memory Optimizations Toward Training Trillion Parameter Models. arXiv:1910.02054 [cs.LG]."},{"key":"e_1_3_2_43_2","unstructured":"J. Hoffmann S. Borgeaud and A. M. a. L. Sifre. 2022. An empirical analysis of compute-optimal large language model training."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2019.2922048"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.09.020"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.112"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2020.110754"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.01.001"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.05.006"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.03.057"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.3233\/JCM-226215"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0113-1"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998278"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2965087"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.12.003"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485477"},{"key":"e_1_3_2_57_2","article-title":"Topical language generation using transformers","author":"Zandie R.","year":"2022","unstructured":"R. Zandie and M. Mahoor. 2022. Topical language generation using transformers. Natural Language Engineering 29, 2 (2022), 337--359.","journal-title":"Natural Language Engineering"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3192097"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.10.063"},{"key":"e_1_3_2_61_2","article-title":"Masked siamese prompt tuning for few-shot natural language understanding","author":"Ni S.","year":"2023","unstructured":"S. Ni and H. Kao. 2023. Masked siamese prompt tuning for few-shot natural language understanding. IEEE Transactions on Artificial Intelligence 5, 2 (2023), 624--633.","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"e_1_3_2_62_2","first-page":"8421","volume-title":"Applied Intelligence","author":"Faal F.","year":"2023","unstructured":"F. Faal, K. Schmitt, and J. Yu. 2023. Reward modeling for mitigating toxicity in transformer-based language models. Applied Intelligence 53, 7 (2023), 8421\u20138435."},{"issue":"1","key":"e_1_3_2_63_2","first-page":"1146","article-title":"Interactive and visual prompt engineering for Ad-hoc task adaptation with large language models","volume":"29","author":"Strobelt H.","year":"2023","unstructured":"H. Strobelt, A. Webson, V. Sanh, and H. P. a. A. Rush. 2023. Interactive and visual prompt engineering for Ad-hoc task adaptation with large language models. IEEE Transactions on Visualization and Computer Graphics 29, 1 (2023), 1146\u20131156.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1010668"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10844-3"},{"key":"e_1_3_2_66_2","article-title":"Bringing legal knowledge to the public by constructing a legal question bank using large-scale pre-trained language model","author":"Yuan M.","year":"2023","unstructured":"M. Yuan, B. Kao, T.-H. Wu, and F. C. a. Y. Chen. 2023. Bringing legal knowledge to the public by constructing a legal question bank using large-scale pre-trained language model. Artificial Intelligence and Law 32, 3 (2023), 769--805.","journal-title":"Artificial Intelligence and Law"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103661"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104431"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00637-1"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"issue":"3","key":"e_1_3_2_71_2","first-page":"771","article-title":"A protein-protein interaction extraction approach based on large pre-trained language model and adversarial training","volume":"16","author":"Tang Z.","year":"2022","unstructured":"Z. Tang, X. Guo, Z. Bai and S. L. a. L. Li. 2022. A protein-protein interaction extraction approach based on large pre-trained language model and adversarial training. KSII Transactions on Internet and Information Systems 16, 3 (2022), 771\u2013791.","journal-title":"KSII Transactions on Internet and Information Systems"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab451"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.3233\/JCM-215594"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00534-z"},{"key":"e_1_3_2_75_2","doi-asserted-by":"crossref","unstructured":"I. Beltagy K. Lo and A. Cohan. 2019. SciBERT: A Pretrained Language Model for Scientific Text. arXiv:1903.10676 [cs.CL].","DOI":"10.18653\/v1\/D19-1371"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00784-w"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c00035"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2023.0140675"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103374"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c01259"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.13164\/mendel.2023.1.055"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03190-3"},{"key":"e_1_3_2_83_2","unstructured":"Y. Liu M. Ott N. Goyal J. Du M. Joshi D. Chen O. Levy M. Lewis and L. Z. a. V. Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv:1907.11692 [cs.CL]."},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3115659"},{"issue":"1","key":"e_1_3_2_85_2","first-page":"16","article-title":"TransBERT: A three-stage pre-training technology for story-ending prediction","volume":"20","author":"Li Z.","year":"2021","unstructured":"Z. Li, X. Ding and T. Liu. 2021. TransBERT: A three-stage pre-training technology for story-ending prediction. ACM Transactions on Asian and Low- Resource Language Information Processing 20, 1 (2021), 16.","journal-title":"ACM Transactions on Asian and Low- Resource Language Information Processing"},{"issue":"8","key":"e_1_3_2_86_2","first-page":"1761","article-title":"Pretraining financial language model with multi-task learning for financial text mining","volume":"58","author":"Liu Z.","year":"2021","unstructured":"Z. Liu, C. Liu, W. Lin, and J. Zhao. 2021. Pretraining financial language model with multi-task learning for financial text mining. Jisuanji Yanjiu yu Fazhan\/Computer Research and Developmen 58, 8 (2021), 1761\u20131772.","journal-title":"Jisuanji Yanjiu yu Fazhan\/Computer Research and Developmen"},{"key":"e_1_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-021-00299-5"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13942"},{"key":"e_1_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3282111"},{"key":"e_1_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40593-023-00336-3"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.3390\/app122111220"},{"key":"e_1_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.07.001"},{"key":"e_1_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3073869"},{"key":"e_1_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3188714"},{"key":"e_1_3_2_95_2","article-title":"GPT-3-Driven pedagogical agents to train children's curious question-asking skills","author":"Abdelghani R.","year":"2023","unstructured":"R. Abdelghani, Y.-H. Wang, X. Yuan, and H. S. a. P.-Y. Oudeyer. 2023. GPT-3-Driven pedagogical agents to train children's curious question-asking skills. International Journal of Artificial Intelligence in Education 2024 (2023).","journal-title":"International Journal of Artificial Intelligence in Education"},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3274199"},{"key":"e_1_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103654"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-022-09602-0"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123555"},{"key":"e_1_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.1002\/asi.24750"},{"issue":"1","key":"e_1_3_2_101_2","first-page":"4","article-title":"Pre-trained language model-based retrieval and ranking for web search","volume":"17","author":"Zou L.","year":"2022","unstructured":"L. Zou, W. Lu, Y. Liu, and S. W. a. D. Yin. 2022. Pre-trained language model-based retrieval and ranking for web search. ACM Transactions on the Web 17, 1 (2022), 4.","journal-title":"ACM Transactions on the Web"},{"key":"e_1_3_2_102_2","unstructured":"Y. Gu L. Dong F. Wei and M. Huang. 2023. Knowledge distillation of large language models. arXiv:2306.08543 [cs.CL]."},{"key":"e_1_3_2_103_2","doi-asserted-by":"crossref","unstructured":"C.-Y. Hsieh C.-L. Li C.-K. Yeh H. Nakhost Y. Fujii A. Ratner R. Krishna and C.-Y. L. a. T. Pfister. 2023. Distilling Step-by-Step! outperforming larger language models with less training data and smaller model sizes. arXiv:2305.02301 [cs.CL].","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"e_1_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2022.3187080"},{"key":"e_1_3_2_105_2","unstructured":"V. Sanh L. Debut and J. C. a. T. Wolf. DistilBERT; a distilled version of BERT: smaller; faster; cheaper and lighter. arXiv:1910.01108 [cs.CL]."},{"key":"e_1_3_2_106_2","unstructured":"S. Shleifer and A. M. Rush. Pre-trained Summarization Distillation. arXiv:2010.13002 [cs.CL]."},{"key":"e_1_3_2_107_2","doi-asserted-by":"crossref","unstructured":"Z. Sun H. Yu X. Song R. Liu and Y. Y. a. D. Zhou. 2020. MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices. arXiv:2004.02984 [cs.CL].","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"e_1_3_2_108_2","doi-asserted-by":"crossref","unstructured":"X. Jiao Y. Yin L. Shang X. Jiang X. Chen L. Li and F. W. a. Q. Liu. 2020. TinyBERT: Distilling BERT for Natural Language Understanding. arXiv:1909.10351 [cs.CL].","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"e_1_3_2_109_2","unstructured":"R. Tang Y. Lu L. Liu L. Mou and O. V. a. J. Lin. 2019. Distilling Task-Specific Knowledge From BERT into simple neural networks. arXiv:1903.12136v1 [cs.CL}."},{"key":"e_1_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.705"},{"key":"e_1_3_2_111_2","unstructured":"T. Li Y. E. Mesbahi I. Kobyzev A. Rashid A. Mahmud N. Anchuri H. Hajimolahoseini and Y. L. a. M. Rezagholizadeh. 2021. A short study on compressing decoder-based language models. arXiv:2110.08460v1 [cs.CL]."},{"key":"e_1_3_2_112_2","unstructured":"E. Frantar and D. Alistarh. 2024. SparseGPT: Massive language models can be accurately pruned in one-Shot. arXiv:2301.00774 [cs.LG]."},{"key":"e_1_3_2_113_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2024.01.016"},{"key":"e_1_3_2_114_2","article-title":"Gephi: an open source software for exploring and manipulating networks","author":"M B.","year":"2009","unstructured":"B. M., H. S., and J. M. 2009. Gephi: an open source software for exploring and manipulating networks. In International AAAI Conference on Weblogs and Social Media.","journal-title":"International AAAI Conference on Weblogs and Social Media"},{"key":"e_1_3_2_115_2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2019.0100668"},{"issue":"4","key":"e_1_3_2_116_2","first-page":"1","article-title":"A deeper look at sheet music composer classification using self-supervised pretraining","volume":"11","author":"Yang D.","year":"2021","unstructured":"D. Yang and K. J. a. T. Tsai. 2021. A deeper look at sheet music composer classification using self-supervised pretraining. Applied Sciences (Switzerland) 11, 4 (2021), 1\u201316.","journal-title":"Applied Sciences (Switzerland)"},{"key":"e_1_3_2_117_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcom.2022.100508"},{"key":"e_1_3_2_118_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114120"},{"key":"e_1_3_2_119_2","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13008"},{"key":"e_1_3_2_120_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.768"},{"key":"e_1_3_2_121_2","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2019.05155"},{"key":"e_1_3_2_122_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.05.023"},{"key":"e_1_3_2_123_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-019-09637-2"},{"key":"e_1_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-018-7253-3"},{"key":"e_1_3_2_125_2","article-title":"Language model-based paired variational autoencoders for robotic language learning","author":"Ozdemir O.","year":"2022","unstructured":"O. Ozdemir, M. Kerzel, C. Weber, and J. L. a. S. Wermter. 2022. Language model-based paired variational autoencoders for robotic language learning. IEEE Transactions on Cognitive and Developmental Systems.","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"e_1_3_2_126_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.107715"},{"key":"e_1_3_2_127_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3111589"},{"key":"e_1_3_2_128_2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2021.0120369"},{"key":"e_1_3_2_129_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"e_1_3_2_130_2","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.559"},{"key":"e_1_3_2_131_2","doi-asserted-by":"publisher","DOI":"10.1145\/3464361"},{"key":"e_1_3_2_132_2","doi-asserted-by":"publisher","DOI":"10.3390\/info12100418"},{"key":"e_1_3_2_133_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3169155"},{"key":"e_1_3_2_134_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23031145"},{"key":"e_1_3_2_135_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107975"},{"key":"e_1_3_2_136_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eij.2022.05.006"},{"key":"e_1_3_2_137_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.07.002"},{"key":"e_1_3_2_138_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2952360"},{"key":"e_1_3_2_139_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118246"},{"key":"e_1_3_2_140_2","article-title":"Multi-Grained attention representation with ALBERT for Aspect-Level sentiment classification","author":"Chen Y.","year":"2021","unstructured":"Y. Chen, L. Kong, and Y. W. a. D. Kong. 2021. Multi-Grained attention representation with ALBERT for Aspect-Level sentiment classification. IEEE Access 9 (2021), 106703--106713.","journal-title":"IEEE Access"},{"key":"e_1_3_2_141_2","article-title":"The biases of Pre-Trained language models: An empirical study on prompt-based sentiment analysis and emotion detection","author":"Mao R.","year":"2022","unstructured":"R. Mao, Q. Liu, K. He, W. Li, and E. Cambria. 2022. The biases of Pre-Trained language models: An empirical study on prompt-based sentiment analysis and emotion detection. IEEE Transactions on Affective Computing 14, 3 (2022), 1743--1753.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"e_1_3_2_142_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3142178"},{"key":"e_1_3_2_143_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-02101-8"},{"key":"e_1_3_2_144_2","doi-asserted-by":"publisher","DOI":"10.1002\/asi.24156"},{"key":"e_1_3_2_145_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.07.027"},{"key":"e_1_3_2_146_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0218194019500347"},{"key":"e_1_3_2_147_2","article-title":"Studying the difference between natural and programming language corpora","author":"Casalnuovo C.","year":"2010","unstructured":"C. Casalnuovo, K. Sagae and P. Devanbu. 2010. Studying the difference between natural and programming language corpora. Empirical Software Engineering.","journal-title":"Empirical Software Engineering"},{"key":"e_1_3_2_148_2","doi-asserted-by":"publisher","DOI":"10.1007\/s44196-021-00019-8"},{"key":"e_1_3_2_149_2","doi-asserted-by":"publisher","DOI":"10.1145\/3497842"},{"key":"e_1_3_2_150_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3065598"},{"key":"e_1_3_2_151_2","article-title":"Biomedical named entity recognition with the combined feature attention and fully-shared multi-task learning","author":"Chen Z. Z. a. A.","year":"2022","unstructured":"Z. Z. a. A. Chen. 2022. Biomedical named entity recognition with the combined feature attention and fully-shared multi-task learning. BMC Bioinformatics.","journal-title":"BMC Bioinformatics"},{"issue":"9","key":"e_1_3_2_152_2","first-page":"936","article-title":"Faster biomedical named entity recognition based on knowledge distillation","volume":"61","author":"Hu B.","year":"2021","unstructured":"B. Hu, T. Geng, G. Deng, L. Duan, and Q. D. Xuebao. 2021. Faster biomedical named entity recognition based on knowledge distillation. Journal of Tsinghua University 61, 9 (2021), 936\u2013942.","journal-title":"Journal of Tsinghua University"},{"key":"e_1_3_2_153_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-020-09822-x"},{"key":"e_1_3_2_154_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.06.001"},{"key":"e_1_3_2_155_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2947898"},{"key":"e_1_3_2_156_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2911320"},{"key":"e_1_3_2_157_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2884540"},{"key":"e_1_3_2_158_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08522-z"},{"key":"e_1_3_2_159_2","first-page":"18","article-title":"efficient open domain question answering with delayed attention in transformer-based models","volume":"2","author":"Siblini W.","year":"2022","unstructured":"W. Siblini, M. Challal, and C. Pasqual. 2022. efficient open domain question answering with delayed attention in transformer-based models. International Journal of Data Warehousing and Mining 2 (2022), 18.","journal-title":"International Journal of Data Warehousing and Mining"},{"key":"e_1_3_2_160_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3097183"},{"issue":"4","key":"e_1_3_2_161_2","first-page":"B-LC2_1-15","article-title":"Automatic short answer grading to pedagogical questions using knowledge graphs and pre-trained models","volume":"37","author":"Araki D. T. a. M.","year":"2022","unstructured":"D. T. a. M. Araki. 2022. Automatic short answer grading to pedagogical questions using knowledge graphs and pre-trained models. Transactions of the Japanese Society for Artificial Intelligence 37, 4 (2022), B-LC2_1-15.","journal-title":"Transactions of the Japanese Society for Artificial Intelligence"},{"issue":"10","key":"e_1_3_2_162_2","article-title":"QA-KGNet: A language model-driven knowledge graph question-answering model","volume":"34","author":"Qiao S.-J.","year":"2023","unstructured":"S.-J. Qiao, G.-P. Yang, Y. Yu, L.-Q. Ran, H. Li, and R. J. X. Bao. 2023. QA-KGNet: A language model-driven knowledge graph question-answering model. Journal of Software 34, 10 (2023).","journal-title":"Journal of Software"},{"key":"e_1_3_2_163_2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8045535"},{"key":"e_1_3_2_164_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107612"},{"key":"e_1_3_2_165_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.148"},{"key":"e_1_3_2_166_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3089099"},{"key":"e_1_3_2_167_2","doi-asserted-by":"publisher","DOI":"10.3390\/info12060223"},{"key":"e_1_3_2_168_2","doi-asserted-by":"crossref","DOI":"10.1007\/s10844-021-00663-8","article-title":"Cross-lingual transfer of abstractive summarizer to less-resource language","author":"\u017dagar A.","year":"2022","unstructured":"A. \u017dagar and M. Robnik-\u0160ikonja. 2022. Cross-lingual transfer of abstractive summarizer to less-resource language. Journal of Intelligent Information Systems.","journal-title":"Journal of Intelligent Information Systems"},{"key":"e_1_3_2_169_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05319-2"},{"issue":"8","key":"e_1_3_2_170_2","first-page":"2075","article-title":"English lexical simplification based on pretrained language representation modeling","volume":"48","author":"Qiang J.-P.","year":"2022","unstructured":"J.-P. Qiang, Z.-Y. Qian, Y. Li, Y.-H. Yuan, Y. Zhu, and Z. Xuebao. 2022. English lexical simplification based on pretrained language representation modeling. Acta Automatica Sinica 48, 8 (2022), 2075\u20132087.","journal-title":"Acta Automatica Sinica"},{"key":"e_1_3_2_171_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3054309"},{"key":"e_1_3_2_172_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.036"},{"key":"e_1_3_2_173_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102535"},{"key":"e_1_3_2_174_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5753693"},{"key":"e_1_3_2_175_2","first-page":"1","article-title":"BERT-Log: Anomaly detection for system logs based on pre-trained language model","volume":"36","author":"Chen S.","unstructured":"S. Chen and H. Liao. BERT-Log: Anomaly detection for system logs based on pre-trained language model. Applied Artificial Intelligence 36, 1.","journal-title":"Applied Artificial Intelligence"},{"issue":"1","key":"e_1_3_2_176_2","first-page":"84","article-title":"MOOC-BERT: Automatically identifying learner cognitive presence from MOOC discussion data","volume":"21","author":"Liu Z.","year":"2023","unstructured":"Z. Liu, X. Kong, H. Chen, S. Liu, and Z. Yang. 2023. MOOC-BERT: Automatically identifying learner cognitive presence from MOOC discussion data. IEEE Transactions on Learning Technologies 21, 1 (2023), 84\u2013901.","journal-title":"IEEE Transactions on Learning Technologies"},{"issue":"3","key":"e_1_3_2_177_2","first-page":"9","article-title":"Improve the response diversity of multi-turn dialogue system by combining knowledge","volume":"49","author":"Li Z.","year":"2022","unstructured":"Z. Li, J. Wu, J. Miao, and X. Yu. 2022. Improve the response diversity of multi-turn dialogue system by combining knowledge. IAENG International Journal of Computer Science 49, 3 (2022), 9.","journal-title":"IAENG International Journal of Computer Science"},{"key":"e_1_3_2_178_2","doi-asserted-by":"publisher","DOI":"10.1111\/jpim.12656"},{"key":"e_1_3_2_179_2","article-title":"An artificial intelligence based data-driven approach for design ideation","author":"Chen L.","year":"2023","unstructured":"L. Chen, P. Wang, H. Dong, F. Shi, J. Han, Y. Guo, P. R. Childs, J. Xiao and C. Wu. 2023. An artificial intelligence based data-driven approach for design ideation. Dyson School of Design Engineering; Imperial College London.","journal-title":"Dyson School of Design Engineering; Imperial College London"},{"key":"e_1_3_2_180_2","article-title":"A process model for generating and evaluating ideas: The use of machine learning and visual analytics to support idea mining","author":"Y. W. A.","year":"2020","unstructured":"W. A. Y. and G. Juell-Skielse. 2020. A process model for generating and evaluating ideas: The use of machine learning and visual analytics to support idea mining. EGOVIS 2020; LNCS 12394; 2020.","journal-title":"EGOVIS"},{"key":"e_1_3_2_181_2","unstructured":"W. Y. Ayele. 2022. A toolbox for idea generation and evaluation: Machine learning; data-driven; and contest-driven approaches to support idea generation. arXiv:2205.09840."},{"key":"e_1_3_2_182_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10798-019-09556-y"},{"key":"e_1_3_2_183_2","doi-asserted-by":"publisher","DOI":"10.1109\/EMR.2023.3272799"},{"key":"e_1_3_2_184_2","first-page":"1","article-title":"Ideas are dimes a dozen: large language models for idea generation in innovation","author":"Girotra K.","year":"2023","unstructured":"K. Girotra, L. Meincke, C. Terwiesch, and K. T. Ulrich. 2023. Ideas are dimes a dozen: large language models for idea generation in innovation. SSRN. 1\u201313.","journal-title":"SSRN"},{"key":"e_1_3_2_185_2","first-page":"13001","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers","author":"Xu Y.","unstructured":"Y. Xu, S. Sheng, B. Xue, L. Fu, X. Wang, and C. Zhou. Exploring and Verbalizing Academic Ideas by Concept Co-occurrence. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers. 13001\u201313027."},{"key":"e_1_3_2_186_2","doi-asserted-by":"crossref","unstructured":"L. Li W. Xu J. Guo R. Zhao X. Li Y. Yuan B. Zhang Y. Jiang Y. Xin R. Dang Y. Rong D. Zhao and T. F. a. L. Bing. 2024. Chain of Ideas: Revolutionizing research in novel idea development with LLM agents. arXiv:2410.13185v1 [cs.AI].","DOI":"10.18653\/v1\/2025.findings-emnlp.477"},{"key":"e_1_3_2_187_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.18"},{"key":"e_1_3_2_188_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1191"},{"volume-title":"Proceedings of the 2024 CHI Conference on Human Factors in C (CHI'24)","author":"Liu Y.","key":"e_1_3_2_189_2","unstructured":"Y. Liu, S. Chen, H. Cheng, M. Yu, X. Ran, A. Mo, and Y. T. a. Y. Huang. How AI processing delays foster creativity: Exploring research question Co- Creation with an LLM-based Agent. In Proceedings of the 2024 CHI Conference on Human Factors in C (CHI'24)."},{"key":"e_1_3_2_190_2","doi-asserted-by":"crossref","unstructured":"J. Baek S. K. Jauhar S. Cucerzan and S. J. Hwang. 2024. ResearchAgent: Iterative research idea generation over scientific literature with large language models. arXiv:2404.07738 [cs.CL].","DOI":"10.18653\/v1\/2025.naacl-long.342"},{"issue":"2025","key":"e_1_3_2_191_2","article-title":"SMAR + NIE IdeaGen: A knowledge graph based node importance estimation with analogical reasoning on large language model for idea generation","volume":"279","author":"Oyelade O. N.","year":"2025","unstructured":"O. N. Oyelade, H. Wang, and K. Rafferty. 2025. SMAR + NIE IdeaGen: A knowledge graph based node importance estimation with analogical reasoning on large language model for idea generation. Expert Systems with Applications 279, 2025 (2025).","journal-title":"Expert Systems with Applications"},{"key":"e_1_3_2_192_2","article-title":"Machine learning for hypothesis generation in biology and medicine: Exploring the latent space of neuroscience and developmental bioelectricity","author":"O'Brien T.","year":"2023","unstructured":"T. O'Brien, J. Stremmel, L. Pio-Lopez, P. McMillen, C. Rasmussen-Ivey, and M. Levin. 2023. Machine learning for hypothesis generation in biology and medicine: Exploring the latent space of neuroscience and developmental bioelectricity. OSF Preprint.","journal-title":"OSF Preprint"},{"key":"e_1_3_2_193_2","doi-asserted-by":"publisher","DOI":"10.1038\/mp.2011.173"},{"key":"e_1_3_2_194_2","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2023.1199736"},{"key":"e_1_3_2_195_2","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/698527"},{"key":"e_1_3_2_196_2","article-title":"Machine Learning as a Tool for Hypothesis Generation","author":"Ludwig J.","year":"2023","unstructured":"J. Ludwig and S. Mullainathan. 2023. Machine Learning as a Tool for Hypothesis Generation. ECONOMIC FINDING.","journal-title":"ECONOMIC FINDING"},{"key":"e_1_3_2_197_2","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abda08"},{"key":"e_1_3_2_198_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jchemed.3c00765"},{"key":"e_1_3_2_199_2","article-title":"Temporal positive-unlabeled learning for biomedical hypothesis generation via risk estimation","author":"Akujuobi U.","year":"2020","unstructured":"U. Akujuobi, J. Chen, M. Elhoseiny, M. Spranger, and X. Zhang. 2020. Temporal positive-unlabeled learning for biomedical hypothesis generation via risk estimation. Advances in Neural Information Processing Systems (NeurIPS 2020) 33 (2020).","journal-title":"Advances in Neural Information Processing Systems (NeurIPS 2020)"},{"key":"e_1_3_2_200_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2991767"},{"key":"e_1_3_2_201_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412684"},{"issue":"170","key":"e_1_3_2_202_2","first-page":"1","article-title":"Scalable and efficient hypothesis testing with random forests","volume":"23","author":"Coleman T.","year":"2022","unstructured":"T. Coleman, W. Peng, and L. Mentch. 2022. Scalable and efficient hypothesis testing with random forests. Journal of Machine LEarning Research 23, 170 (2022), 1\u201335.","journal-title":"Journal of Machine LEarning Research"},{"key":"e_1_3_2_203_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00090"},{"key":"e_1_3_2_204_2","article-title":"Phenomenal yet puzzling: Testing inductive reasoning capabilities of language models with hypothesis refinement","author":"Qiu L.","year":"2024","unstructured":"L. Qiu, L. Jiang, X. Lu, M. Sclar, V. Pyatkin, C. Bhagavatula, B. Wang, Y. Kim, Y. Choi, N. Dziri, and X. Ren. 2024. Phenomenal yet puzzling: Testing inductive reasoning capabilities of language models with hypothesis refinement. ICLR'24.","journal-title":"ICLR'24"},{"key":"e_1_3_2_205_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.nlp4science-1.10"},{"key":"e_1_3_2_206_2","article-title":"Large language models for automated open-domain scientific hypotheses discovery","author":"Yang Z.","year":"2024","unstructured":"Z. Yang, X. Du, J. Li, J. Zheng, and S. P. a. E. Cambria. 2024. Large language models for automated open-domain scientific hypotheses discovery. ACL'24.","journal-title":"ACL'24"},{"key":"e_1_3_2_207_2","article-title":"Large language models as biomedical hypothesis generators: A comprehensive evaluation","author":"Qi B.","year":"2024","unstructured":"B. Qi, K. Zhang, K. Tian, H. Li, Z.-R. Chen, S. Zeng, E. Hua, H. Jinfang, and B. Zhou. 2024. Large language models as biomedical hypothesis generators: A comprehensive evaluation. COLM'24.","journal-title":"COLM'24"},{"key":"e_1_3_2_208_2","unstructured":"I. Ciuc\u0103 Y.-S. Ting S. Kruk and K. Iyer. 2023. Harnessing the power of adversarial prompting and large language models for robust hypothesis generation in astronomy. arXiv:2306.11648."},{"key":"e_1_3_2_209_2","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2400555"},{"key":"e_1_3_2_210_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00615"},{"key":"e_1_3_2_211_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.conll-babylm.2"},{"issue":"120","key":"e_1_3_2_212_2","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus W.","year":"2022","unstructured":"W. Fedus, B. Zoph, and N. Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine LEarning Research 23, 120 (2022), 1\u201339.","journal-title":"Journal of Machine LEarning Research"},{"key":"e_1_3_2_213_2","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML'23)","author":"Frantar E.","year":"2023","unstructured":"E. Frantar and D. Alistarh. 2023. SparseGPT: massive language models can be accurately pruned in one-shot. Proceedings of the 40th International Conference on Machine Learning (ICML'23)."},{"key":"e_1_3_2_214_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.conll-babylm.3"},{"key":"e_1_3_2_215_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.conll-babylm.8"},{"key":"e_1_3_2_216_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.31"},{"key":"e_1_3_2_217_2","first-page":"5514","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers","author":"Chen Z.","unstructured":"Z. Chen, Q. Gao, A. Bosselut, A. Sabharwal, and K. Richardson. DISCO: Distilling counterfactuals with large language models. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers. 5514\u20135528."},{"issue":"209","key":"e_1_3_2_218_2","first-page":"1","article-title":"Ranking and tuning pre-trained models: A new paradigm for exploiting model hubs","volume":"23","author":"You K.","year":"2022","unstructured":"K. You, Y. Liu, Z. Zhang, J. Wang, M. I. Jordan, and M. Long. 2022. Ranking and tuning pre-trained models: A new paradigm for exploiting model hubs. Journal of Machine LEarning Research 23, 209 (2022), 1--47.","journal-title":"Journal of Machine LEarning Research"},{"volume-title":"Proceedings of the 40th International Conference on MAchine Learning (ICML'23)","author":"Driess D.","key":"e_1_3_2_219_2","unstructured":"D. Driess, F. Xia, M. S. M. Sajjadi, C. Lynch, A. Chowdhery, B. Ichter, A. Wahid, J. Tompson, Q. Vuong, T. Yu, W. Huang, Y. Chebotar, and P. e. a. Sermanet. PaLM-E: an embodied multimodal language model. Proceedings of the 40th International Conference on MAchine Learning (ICML'23)."},{"key":"e_1_3_2_220_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.341"},{"key":"e_1_3_2_221_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.150"},{"key":"e_1_3_2_222_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.535"},{"key":"e_1_3_2_223_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25501"},{"key":"e_1_3_2_224_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25472"},{"key":"e_1_3_2_225_2","article-title":"End-to-End Zero-Shot HOI detection via vision and language knowledge distillation","author":"Wu M.","year":"2023","unstructured":"M. Wu, J. Gu, Y. Shen, M. Lin, and C. C. a. X. Sun. 2023. End-to-End Zero-Shot HOI detection via vision and language knowledge distillation. AAAI Conference on Artificial Intelligence.","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_2_226_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25391"},{"issue":"97","key":"e_1_3_2_227_2","first-page":"1","article-title":"Unlabeled data help in graph-based semi-supervised learning: A bayesian nonparametrics perspective","volume":"23","author":"Sanz-Alonso D.","year":"2022","unstructured":"D. Sanz-Alonso and R. Yang. 2022. Unlabeled data help in graph-based semi-supervised learning: A bayesian nonparametrics perspective. Journal of Machine LEarning Research 23, 97 (2022), 1\u201328.","journal-title":"Journal of Machine LEarning Research"},{"key":"e_1_3_2_228_2","first-page":"1","article-title":"Joint inference of multiple graphs from matrix polynomials","volume":"76","author":"Navarro M.","year":"2022","unstructured":"M. Navarro, Y. Wang, A. G. Marques, C. Uhler, and S. Segarra. 2022. Joint inference of multiple graphs from matrix polynomials. Journal of Machine LEarning Research 76 (2022), 1\u201335.","journal-title":"Journal of Machine LEarning Research"},{"issue":"89","key":"e_1_3_2_229_2","first-page":"1","article-title":"Machine learning on graphs: A model and comprehensive taxonomy","volume":"23","author":"Chami I.","year":"2022","unstructured":"I. Chami, S. Abu-El-Haija, B. Perozzi, C. R\u00e9, and K. Murphy. 2022. Machine learning on graphs: A model and comprehensive taxonomy. Journal of Machine LEarning Research 23, 89 (2022), 1--64.","journal-title":"Journal of Machine LEarning Research"},{"key":"e_1_3_2_230_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00022"},{"key":"e_1_3_2_231_2","article-title":"Multimodal analogical reasoning over knowledge graphs","author":"Zhang N.","year":"2023","unstructured":"N. Zhang, L. Li, X. Chen, X. Liang, S. Deng, and H. Chen. 2023. Multimodal analogical reasoning over knowledge graphs. ICLR'23.","journal-title":"ICLR'23"},{"key":"e_1_3_2_232_2","article-title":"DeepGAR: Deep graph learning for analogical reasoning","author":"Chowdhury T.","year":"2022","unstructured":"Ling T. Chowdhury, J. Jiang, J. Wang, X. Zhang, H. Chen, and L. Zhao. 2022. DeepGAR: Deep graph learning for analogical reasoning. 2022 IEEE International Conference on Data Mining (ICDM'22).","journal-title":"2022 IEEE International Conference on Data Mining (ICDM'22)"},{"key":"e_1_3_2_233_2","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Hakami H.","year":"2022","unstructured":"H. Hakami, M. Hakami, A. Mandya, and D. Bollegala. 2022. Learning to Borrow\u2013 Relation representation for without-mention entity-pairs for knowledge graph completion. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies."},{"key":"e_1_3_2_234_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00028"},{"issue":"1","key":"e_1_3_2_235_2","article-title":"Learning heterogeneous subgraph representations for team discovery","volume":"26","author":"Rad R. H.","year":"2023","unstructured":"R. H. Rad, H. Nguyen, F. Al-Obeidat, E. Bagheri, M. Kargar, D. Srivastava, J. Szlichta, and F. Zarrinkalam. 2023. Learning heterogeneous subgraph representations for team discovery. Information Retrieval 26, 1-2 (2023).","journal-title":"Information Retrieval"},{"key":"e_1_3_2_236_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-022-09412-z"},{"key":"e_1_3_2_237_2","article-title":"Hypergraph attribute attention network for community recommendation","author":"Li K.","year":"2023","unstructured":"K. Li, W.-D. Xi, X.-X. Xing, and C.-D. Wang. 2023. Hypergraph attribute attention network for community recommendation. In IEEE International Conference on Data Mining (ICDM'23).","journal-title":"IEEE International Conference on Data Mining (ICDM'23)"},{"key":"e_1_3_2_238_2","doi-asserted-by":"crossref","DOI":"10.1109\/ICDM58522.2023.00140","article-title":"Decision-focused graph neural networks for graph learning and optimization","author":"Liu Y.","year":"2023","unstructured":"Y. Liu, C. Zhou, P. Zhang, S. Zhang, X. Zhang, Z. Li, and H. Chen. 2023. Decision-focused graph neural networks for graph learning and optimization. In 2023 IEEE International Conference on Data Mining (ICDM'23).","journal-title":"2023 IEEE International Conference on Data Mining (ICDM'23)"},{"key":"e_1_3_2_239_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.895"},{"key":"e_1_3_2_240_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.785"},{"issue":"219","key":"e_1_3_2_241_2","first-page":"1","article-title":"Structural agnostic modeling: adversarial learning of causal graphs","volume":"23","author":"Kalainathan D.","year":"2022","unstructured":"D. Kalainathan, O. Goudet, I. Guyon, and D. L.-P. a. M. Sebag. 2022. Structural agnostic modeling: adversarial learning of causal graphs. Journal of Machine LEarning Research 23, 219 (2022), 1\u201362.","journal-title":"Journal of Machine LEarning Research"},{"volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua","author":"Wu Z.","key":"e_1_3_2_242_2","unstructured":"Z. Wu, A. Geiger, J. Rozner, E. Kreiss, H. Lu, T. Icard, C. Potts, and N. Goodman. Causal distillation for language models. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua."},{"issue":"295","key":"e_1_3_2_243_2","first-page":"1","article-title":"Semiparametric inference for causal effects in graphical models with hidden variables","volume":"23","author":"Bhattacharya R.","year":"2022","unstructured":"R. Bhattacharya, R. Nabi, and I. Shpitser. 2022. Semiparametric inference for causal effects in graphical models with hidden variables. Journal of Machine LEarning Research 23, 295 (2022), 1\u201376.","journal-title":"Journal of Machine LEarning Research"},{"key":"e_1_3_2_244_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00554"},{"issue":"345","key":"e_1_3_2_245_2","first-page":"1","article-title":"Constraint Reasoning Embedded Structured Prediction","volume":"23","author":"Jiang N.","year":"2022","unstructured":"N. Jiang, M. Zhang, and W.-J. v. H. a. Y. Xue. 2022. Constraint Reasoning Embedded Structured Prediction. Journal of Machine Learning Research 23, 345 (2022), 1--40.","journal-title":"Journal of Machine Learning Research"},{"issue":"85","key":"e_1_3_2_246_2","first-page":"1","article-title":"A distribution free conditional independence test with applications to causal discovery","volume":"23","author":"Cai Z.","year":"2022","unstructured":"Z. Cai, R. Li, and Y. Zhang. 2022. A distribution free conditional independence test with applications to causal discovery. Journal of Machine Learning Research 23, 85 (2022), 1\u221241.","journal-title":"Journal of Machine Learning Research"},{"issue":"44","key":"e_1_3_2_247_2","first-page":"1","article-title":"PAC guarantees and effective algorithms for detecting novel categories","volume":"23","author":"Liu S.","year":"2022","unstructured":"S. Liu, R. Garrepalli, D. Hendrycks, A. Fern, and D. M. a. T. G. Dietterich. 2022. PAC guarantees and effective algorithms for detecting novel categories. Journal of Machine Learning Research 23, 44 (2022), 1\u201347.","journal-title":"Journal of Machine Learning Research"},{"issue":"109","key":"e_1_3_2_248_2","first-page":"1","article-title":"Conditions and assumptions for constraint-based causal structure learning","volume":"23","author":"Sadeghi K.","year":"2022","unstructured":"K. Sadeghi and T. Soo. 2022. Conditions and assumptions for constraint-based causal structure learning. Journal of Machine Learning Research 23, 109 (2022), 1\u201334.","journal-title":"Journal of Machine Learning Research"},{"issue":"335","key":"e_1_3_2_249_2","first-page":"1","article-title":"Causal aggregation: estimation and inference of causal effects by constraint-based data fusion","volume":"23","author":"Gimenez J. R.","year":"2022","unstructured":"J. R. Gimenez and D. Rothenh\u00e4usler. 2022. Causal aggregation: estimation and inference of causal effects by constraint-based data fusion. Journal of Machine Learning Research 23, 335 (2022), 1\u201360.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_250_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00076"},{"key":"e_1_3_2_251_2","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3618505"},{"key":"e_1_3_2_252_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26452"},{"key":"e_1_3_2_253_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00567"},{"key":"e_1_3_2_254_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00642"},{"key":"e_1_3_2_255_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00462"},{"key":"e_1_3_2_256_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00122"},{"key":"e_1_3_2_257_2","first-page":"414","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML'23)","author":"Zhang Tianjun","year":"2023","unstructured":"Tianjun Zhang, Fangchen Liu, Justin Wong, Pieter Abbeel, and J. E. Gonzalez. 2023. The wisdom of hindsight makes language models better instruction followers. Proceedings of the 40th International Conference on Machine Learning (ICML'23) (2023), 414."},{"key":"e_1_3_2_258_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25094"},{"key":"e_1_3_2_259_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26465"},{"key":"e_1_3_2_260_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20521"},{"key":"e_1_3_2_261_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.15"},{"volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Zhang Y.","key":"e_1_3_2_262_2","unstructured":"Y. Zhang, Y. Meng, X. Wang, S. Wang, and J. Han. Seed-guided topic discovery with out-of-vocabulary seeds. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies."},{"key":"e_1_3_2_263_2","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Maharana A.","year":"2023","unstructured":"A. Maharana and M. Bansal. 2023. On curriculum learning for commonsense reasoning. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies."},{"key":"e_1_3_2_264_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.260"},{"volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computa","author":"Plenz M.","key":"e_1_3_2_265_2","unstructured":"M. Plenz, J. Opitz, P. Heinisch, P. Cimiano, and A. Frank. Similarity-weighted construction of contextualized commonsense knowledge graphs for knowledge-intense argumentation tasks. Proceedings of the 61st Annual Meeting of the Association for Computa."},{"key":"e_1_3_2_266_2","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Rawat B. P. S.","year":"2023","unstructured":"B. P. S. Rawat, S. Kovaly, H. Yu, and W. Pigeon. 2023. ScAN: Suicide attempt and ideation events dataset. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies."},{"key":"e_1_3_2_267_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.33"},{"key":"e_1_3_2_268_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.108"},{"key":"e_1_3_2_269_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.55"},{"key":"e_1_3_2_270_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.558"},{"key":"e_1_3_2_271_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.104"},{"key":"e_1_3_2_272_2","unstructured":"C. Lu C. Lu R. T. Lange J. Foerster J. Clune and D. Ha. 2024. The AI Scientist: Towards fully automated open-ended scientific discovery. arXiv:2408.06292 [cs.AI]."},{"key":"e_1_3_2_273_2","article-title":"LangGraph x GPT Researcher","author":"Elovic A.","year":"2025","unstructured":"A. Elovic. 2025. LangGraph x GPT Researcher. GitHub. [Online] . Available: https:\/\/github.com\/assafelovic\/gpt-researcher\/tree\/master\/multi_agents. [Accessed 2 1 2025].","journal-title":"GitHub"},{"key":"e_1_3_2_274_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.347"},{"key":"e_1_3_2_275_2","volume-title":"arXiv:2411.02382 [cs.CL]","author":"Xiong G.","year":"2024","unstructured":"G. Xiong, E. Xie, A. H. Shariatmadari, S. Guo, S. Bekiranov, and A. Zhang. 2024. Improving scientific hypothesis generation with knowledge grounded large language models. arXiv:2411.02382 [cs.CL]."},{"key":"e_1_3_2_276_2","unstructured":"Y. Zhang X. Wang J. Liang S. Xia L. Chen and Y. Xiao. 2024. Chain-of-Knowledge: Integrating knowledge reasoning into large language models by learning from knowledge graphs. arXiv:2407.00653 [cs.CL]."},{"key":"e_1_3_2_277_2","doi-asserted-by":"crossref","unstructured":"K. Li T. Zhang X. Wu H. Luo J. Glass and H. Meng. 2024. Decoding on Graphs: Faithful and sound reasoning on knowledge graphs through generation of well-formed chains. arXiv:2410.18415v1 (2024).","DOI":"10.18653\/v1\/2025.acl-long.1186"},{"key":"e_1_3_2_278_2","unstructured":"C. Dilmegani. 2023. Large language models: complete guide in 2023. [Online] . Available: https:\/\/research.aimultiple.com\/large-language-models\/. [Accessed 2 8 2023]."},{"key":"e_1_3_2_279_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597307"},{"key":"e_1_3_2_280_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25496"},{"key":"e_1_3_2_281_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.72"},{"key":"e_1_3_2_282_2","doi-asserted-by":"publisher","DOI":"10.25082\/IJAH.2023.01.003"},{"key":"e_1_3_2_283_2","volume-title":"ICLR 2024","author":"Wang R.","year":"2024","unstructured":"R. Wang, E. Zelikman, G. Poesia, Y. Pu, N. Haber, and N. Goodman. 2024. Hypothesis search: Inductive reasoning with language models. ICLR 2024."},{"key":"e_1_3_2_284_2","unstructured":"B. Qi K. Zhang H. Li K. Tian S. Zeng Z.-R. Chen and B. Zhou. 2023. Large language models are zero shot hypothesis proposers. arXiv:2311.05965."},{"key":"e_1_3_2_285_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2023.102642"},{"key":"e_1_3_2_286_2","unstructured":"T. B. Grant. 2023. How AI and language models can change the energy industry. [Online] . Available: https:\/\/www.cegal.com\/en\/resources\/how-ai-and-language-models-can-change-the-energy-industry. [Accessed 2 8 2023]"},{"key":"e_1_3_2_287_2","unstructured":"S. Takagi and R. Y. a. W. Kumaga. 2023. Towards autonomous hypothesis verification via language models with minimal guidance. arXiv:2311.09706v1."},{"key":"e_1_3_2_288_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.conll-1.21"},{"key":"e_1_3_2_289_2","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Dziri N.","year":"2023","unstructured":"N. Dziri, S. Milton, M. Yu, O. Zaiane, and S. Reddy. 2023. On the origin of hallucinations in conversational models: Is it the datasets or the models? In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies."},{"key":"e_1_3_2_290_2","doi-asserted-by":"publisher","DOI":"10.1109\/MITP.2023.3275489"},{"key":"e_1_3_2_291_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00873-0"},{"issue":"2023","key":"e_1_3_2_292_2","article-title":"ChatGPT for Good? On opportunities and challenges of large language models for education","volume":"103","author":"Kasneci E.","year":"2023","unstructured":"E. Kasneci, K. Sessler, S. K. \u0308uchemann, M. Bannert, D. Dementieva, F. Fischer, U. Gasser, G. Groh, S. G. \u0308unnemann, E. H. \u0308ullermeier, S. Krusche, G. Kutyniok, T. Michaeli, C. Nerdel, and J. \u0308urgenPfeffer. 2023. ChatGPT for Good? On opportunities and challenges of large language models for education. Learning and Individual Differences 103, 2023 (2023), 1--13.","journal-title":"Learning and Individual Differences"},{"key":"e_1_3_2_293_2","doi-asserted-by":"crossref","unstructured":"T. Eloundou S. Manning P. Mishkin and D. Rock. 2023. GPTs are GPTs: An early look at the labor market impact potential of large language models. arXiv:2303.10130v4 [econ.GN].","DOI":"10.1126\/science.adj0998"},{"key":"e_1_3_2_294_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06259-9"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T14:30:49Z","timestamp":1765031449000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":293,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3774628"],"URL":"https:\/\/doi.org\/10.1145\/3774628","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"type":"print","value":"0360-0300"},{"type":"electronic","value":"1557-7341"}],"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2023-09-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}