{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:57:23Z","timestamp":1781197043538,"version":"3.54.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473136"],"award-info":[{"award-number":["62473136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132208","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T17:20:10Z","timestamp":1774545610000},"page":"132208","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Socratic Elenchus-inspired multi-agent debate for mitigating hallucinations in large language models"],"prefix":"10.1016","volume":"320","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2587-3567","authenticated-orcid":false,"given":"Jiacheng","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6643-7369","authenticated-orcid":false,"given":"Tao","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1833-9019","authenticated-orcid":false,"given":"Xiaoyin","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132208_bib0001","series-title":"13th IEEE annual computing and communication workshop and conference","first-page":"351","article-title":"Prompting large language models with the socratic method","author":"Chang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0002","series-title":"Proceedings of the 63rd annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"30187","article-title":"Stochastic chameleons: Irrelevant context hallucinations reveal class-based (mis)generalization in LLMs","author":"Cheng","year":"2025"},{"key":"10.1016\/j.eswa.2026.132208_bib0003","series-title":"The twelfth international conference on learning representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","first-page":"1","article-title":"Dola: Decoding by contrasting layers improves factuality in large language models","author":"Chuang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132208_bib0004","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","first-page":"1419","article-title":"Lookback lens: Detecting and mitigating contextual hallucinations in large language models using only attention maps","author":"Chuang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132208_bib0005","article-title":"Training verifiers to solve math word problems","volume":"abs\/2110.14168","author":"Cobbe","year":"2021","journal-title":"CoRR"},{"key":"10.1016\/j.eswa.2026.132208_bib0006","series-title":"Proceedings of the 41st international conference on machine learning","first-page":"11733","article-title":"Improving factuality and reasoning in language models through multiagent debate","volume":"vol. 235","author":"Du","year":"2024"},{"key":"10.1016\/j.eswa.2026.132208_bib0007","series-title":"Proceedings of the 31st international conference on computational linguistics","first-page":"10554","article-title":"Counterfactual debating with preset stances for hallucination elimination of LLMs","author":"Fang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132208_bib0008","series-title":"Proceedings of the 40th international conference on machine learning","first-page":"10867","article-title":"The unreasonable effectiveness of few-shot learning for machine translation","volume":"vol. 202","author":"Garcia","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0009","series-title":"Findings of the association for computational linguistics: EMNLP 2020","first-page":"3662","article-title":"The box is in the pen: Evaluating commonsense reasoning in neural machine translation","author":"He","year":"2020"},{"key":"10.1016\/j.eswa.2026.132208_bib0010","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1162\/tacl_a_00642","article-title":"Exploring human-like translation strategy with large language models","volume":"12","author":"He","year":"2024","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.1016\/j.eswa.2026.132208_bib0011","unstructured":"Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., Kim, Y. J., Afify, M., & Awadalla, H. H. (2023). How good are GPT models at machine translation? A comprehensive evaluation. CoRR, 10.48550\/ARXIV.2302.09210."},{"key":"10.1016\/j.eswa.2026.132208_bib0012","series-title":"The twelfth international conference on learning representations","first-page":"1","article-title":"Large language models cannot self-correct reasoning yet","author":"Huang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132208_bib0013","series-title":"Proceedings of the workshop on generative AI and knowledge graphs (genAIK)","first-page":"43","article-title":"On reducing factual hallucinations in graph-to-text generation using large language models","author":"Iarosh","year":"2025"},{"key":"10.1016\/j.eswa.2026.132208_bib0014","unstructured":"Kadavath, S., Conerly, T., Askell, A., Henighan, T., Drain, D., Perez, E., Schiefer, N., Hatfield-Dodds, Z., DasSarma, N., Tran-Johnson, E., Johnston, S., Showk, S. E., Jones, A., Elhage, N., Hume, T., Chen, A., Bai, Y., Bowman, S., Fort, S., Ganguli, D., Hernandez, D., Jacobson, J., Kernion, J., Kravec, S., Lovitt, L., Ndousse, K., Olsson, C., Ringer, S., Amodei, D., Brown, T., Clark, J., Joseph, N., Mann, B., McCandlish, S., Olah, C., & Kaplan, J. (2022). Language models (mostly) know what they know. CoRR, 10.48550\/ARXIV.2207.05221."},{"issue":"9","key":"10.1016\/j.eswa.2026.132208_bib0015","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1007\/s10462-024-10888-y","article-title":"Large language models (LLMs): survey, technical frameworks, and future challenges","volume":"57","author":"Kumar","year":"2024","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.eswa.2026.132208_bib0016","series-title":"Advances in neural information processing systems","first-page":"41451","article-title":"Inference-time intervention: Eliciting truthful answers from a language model","volume":"vol. 36","author":"Li","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0017","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"12286","article-title":"Contrastive decoding: Open-ended text generation as optimization","author":"Li","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0018","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","first-page":"17889","article-title":"Encouraging divergent thinking in large language models through multi-agent debate","author":"Liang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132208_bib0019","series-title":"Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"3214","article-title":"TruthfulQA: Measuring how models mimic human falsehoods","author":"Lin","year":"2022"},{"key":"10.1016\/j.eswa.2026.132208_bib0020","series-title":"Advances in neural information processing systems","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume":"vol. 36","author":"Madaan","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0021","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics","first-page":"1906","article-title":"On faithfulness and factuality in abstractive summarization","author":"Maynez","year":"2020"},{"key":"10.1016\/j.eswa.2026.132208_bib0022","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1162\/tacl_a_00494","article-title":"Reducing conversational agents\u2019 overconfidence through linguistic calibration","volume":"10","author":"Mielke","year":"2022","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.1016\/j.eswa.2026.132208_bib0023","series-title":"Advances in neural information processing systems","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"vol. 35","author":"Ouyang","year":"2022"},{"key":"10.1016\/j.eswa.2026.132208_bib0024","series-title":"Proceedings of the 2021 conference of the north american chapter of the association for computational linguistics: Human language technologies","first-page":"2080","article-title":"Are NLP models really able to solve simple math word problems?","author":"Patel","year":"2021"},{"key":"10.1016\/j.eswa.2026.132208_bib0025","series-title":"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)","first-page":"455","article-title":"Interactive-chain-prompting: Ambiguity resolution for crosslingual conditional generation with interaction","author":"Pilault","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0026","unstructured":"Prasad, P. S., & Nguyen, M. N. (2025). When two LLMs debate, both think they\u2019ll win. CoRR, 10.48550\/ARXIV.2505.19184."},{"key":"10.1016\/j.eswa.2026.132208_bib0027","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"4177","article-title":"The art of SOCRATIC QUESTIONING: Recursive thinking with large language models","author":"Qi","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0028","series-title":"Advances in neural information processing systems","first-page":"8634","article-title":"Reflexion: language agents with verbal reinforcement learning","volume":"vol. 36","author":"Shinn","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0029","series-title":"Advances in neural information processing systems","first-page":"8634","article-title":"Reflexion: language agents with verbal reinforcement learning","volume":"vol. 36","author":"Shinn","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0030","series-title":"NeurIPS 2023 foundation models for decision making workshop","first-page":"1","article-title":"GPT-4 doesn\u2019t know it\u2019s wrong: An analysis of iterative prompting for reasoning problems","author":"Stechly","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0031","series-title":"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)","first-page":"4149","article-title":"CommonsenseQA: A question answering challenge targeting commonsense knowledge","author":"Talmor","year":"2019"},{"key":"10.1016\/j.eswa.2026.132208_bib0032","series-title":"NeurIPS 2023 foundation models for decision making workshop","first-page":"1","article-title":"Investigating the effectiveness of self-critiquing in LLMs solving planning tasks","author":"Valmeekam","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0033","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"6106","article-title":"Rethinking the bounds of LLM reasoning: Are multi-agent discussions the key?","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132208_bib0034","series-title":"The eleventh international conference on learning representations","first-page":"1","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0035","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"13484","article-title":"Self-instruct: Aligning language models with self-generated instructions","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132208_bib0036","series-title":"Advances in neural information processing systems","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"vol. 35","author":"Wei","year":"2022"},{"key":"10.1016\/j.eswa.2026.132208_bib0037","series-title":"The twelfth international conference on learning representations","first-page":"1","article-title":"Can LLMs express their uncertainty? An empirical evaluation of confidence elicitation in LLMs","author":"Xiong","year":"2024"},{"key":"10.1016\/j.eswa.2026.132208_bib0038","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"3602","article-title":"Self-contrast: Better reflection through inconsistent solving perspectives","author":"Zhang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132208_bib0039","series-title":"Proceedings of the 23rd annual meeting of the special interest group on discourse and dialogue","first-page":"516","article-title":"Toward self-learning end-to-end task-oriented dialog systems","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2026.132208_bib0040","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"1946","article-title":"Self-alignment for factuality: Mitigating hallucinations in LLMs via self-evaluation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132208_bib0041","series-title":"Findings of the association for computational linguistics: NAACL 2025","first-page":"8218","article-title":"Alleviating hallucinations of large language models through induced hallucinations","author":"Zhang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132208_bib0042","unstructured":"Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., Chen, Y., Wang, L., Luu, A. T., Bi, W., Shi, F., & Shi, S. (2023). Siren\u2019s song in the AI ocean: A survey on hallucination in large language models. CoRR, 10.48550\/ARXIV.2309.01219."}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011218?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011218?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:59:27Z","timestamp":1781193567000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426011218"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":42,"alternative-id":["S0957417426011218"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132208","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Socratic Elenchus-inspired multi-agent debate for mitigating hallucinations in large language models","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132208","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132208"}}