{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:49:42Z","timestamp":1785912582621,"version":"3.56.0"},"reference-count":90,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100014717","name":"Youth Science Fund Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005153","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["KZ37117501"],"award-info":[{"award-number":["KZ37117501"]}],"id":[{"id":"10.13039\/501100005153","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306024"],"award-info":[{"award-number":["62306024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004921","name":"Shanghai Jiao Tong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004921","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012282","name":"Beijing Innovation Center for Future Chip","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012282","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["23AFX002"],"award-info":[{"award-number":["23AFX002"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["21&ZD200"],"award-info":[{"award-number":["21&ZD200"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.ipm.2026.105030","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T12:57:51Z","timestamp":1782824271000},"page":"105030","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Benchmarking multi-step legal reasoning and analyzing Chain-of-Thought effects in Large Language Models"],"prefix":"10.1016","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8417-0898","authenticated-orcid":false,"given":"Wenhan","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2390-0261","authenticated-orcid":false,"given":"Xinbo","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4627-6649","authenticated-orcid":false,"given":"Lanxin","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9701-7155","authenticated-orcid":false,"given":"Jinhua","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5914-7590","authenticated-orcid":false,"given":"Lei","family":"Sha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ipm.2026.105030_b1","series-title":"Proceedings of the 18th conference of the European chapter of the association for computational linguistics: student research workshop","first-page":"225","article-title":"Large language models for mathematical reasoning: progresses and challenges","author":"Ahn","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b2","series-title":"Handbook of legal reasoning and argumentation","first-page":"637","article-title":"Coherence and systematization in law","author":"Amaya","year":"2018"},{"issue":"6","key":"10.1016\/j.ipm.2026.105030_b3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3777009","article-title":"Natural language processing for the legal domain: A survey of tasks, datasets, models, and challenges","volume":"58","author":"Ariai","year":"2025","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.ipm.2026.105030_b4","series-title":"Proceedings of the symposium on computer science and law","first-page":"136","article-title":"Translating legalese: Enhancing public understanding of court opinions with legal summarizers","author":"Ash","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b5","series-title":"Artificial intelligence and legal analytics: New tools for law practice in the digital age","author":"Ashley","year":"2017"},{"key":"10.1016\/j.ipm.2026.105030_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2020.103387","article-title":"Explanation in AI and law: past, present and future","volume":"289","author":"Atkinson","year":"2020","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.ipm.2026.105030_b7","series-title":"Research handbook on insider trading","first-page":"1","article-title":"An overview of insider trading law and policy: An introduction to the research handbook on insider trading","author":"Bainbridge","year":"2013"},{"key":"10.1016\/j.ipm.2026.105030_b8","series-title":"Proceedings of the eighteenth international conference on artificial intelligence and law","first-page":"175","article-title":"On the relevance of algorithmic decision predictors for judicial decision making","author":"Bex","year":"2021"},{"issue":"Volume 6, 2014","key":"10.1016\/j.ipm.2026.105030_b9","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1146\/annurev-financial-110613-034422","article-title":"Insider trading controversies: a literature review","volume":"6","author":"Bhattacharya","year":"2014","journal-title":"Annual Review of Financial Economics"},{"issue":"1","key":"10.1016\/j.ipm.2026.105030_b10","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1111\/1540-6261.00416","article-title":"The world price of insider trading","volume":"57","author":"Bhattacharya","year":"2002","journal-title":"The Journal of Finance"},{"issue":"5","key":"10.1016\/j.ipm.2026.105030_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2026.104667","article-title":"CLER: A benchmark for Chinese litigation evidence reasoning","volume":"63","author":"Bi","year":"2026","journal-title":"Information Processing & Management"},{"issue":"2","key":"10.1016\/j.ipm.2026.105030_b12","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s10506-020-09270-4","article-title":"Legal requirements on explainability in machine learning","volume":"29","author":"Bibal","year":"2021","journal-title":"Artificial Intelligence and Law"},{"issue":"2","key":"10.1016\/j.ipm.2026.105030_b13","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1007\/s10506-023-09356-9","article-title":"The black box problem revisited. real and imaginary challenges for automated legal decision making","volume":"32","author":"Bro\u017cek","year":"2024","journal-title":"Artificial Intelligence and Law"},{"key":"10.1016\/j.ipm.2026.105030_b14","series-title":"Proceedings of the 18th conference of the European chapter of the association for computational linguistics (volume 1: long papers)","first-page":"2015","article-title":"Answering legal questions from laymen in german civil law system","author":"B\u00fcttner","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b15","series-title":"InternLM2 technical report","author":"Cai","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b16","series-title":"Lexglue: A benchmark dataset for legal language understanding in english","author":"Chalkidis","year":"2022"},{"issue":"5","key":"10.1016\/j.ipm.2026.105030_b17","doi-asserted-by":"crossref","first-page":"73","DOI":"10.3138\/utlj-2023-0003","article-title":"Explainability and the epistemic division of labour in adjudication","volume":"73","author":"Chiao","year":"2023","journal-title":"University of Toronto Law Journal"},{"key":"10.1016\/j.ipm.2026.105030_b18","series-title":"Chatlaw: A multi-agent collaborative legal assistant with knowledge graph enhanced mixture-of-experts large language model","author":"Cui","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b19","series-title":"Deepseek-V3 technical report","author":"DeepSeek-AI","year":"2025"},{"key":"10.1016\/j.ipm.2026.105030_b20","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"13997","article-title":"Syllogistic reasoning for legal judgment analysis","author":"Deng","year":"2023"},{"key":"10.1016\/j.ipm.2026.105030_b21","series-title":"Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"6480","article-title":"Reasoning and planning with large language models in code development","author":"Ding","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b22","series-title":"How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning","author":"Dutta","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b23","series-title":"Lexam: Benchmarking legal reasoning on 340 law exams","author":"Fan","year":"2025"},{"key":"10.1016\/j.ipm.2026.105030_b24","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","first-page":"7933","article-title":"LawBench: benchmarking legal knowledge of large language models","author":"Fei","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b25","series-title":"Proceedings of the 46th international ACM SIGIR conference on research and development in information retrieval","first-page":"3285","article-title":"Context-aware classification of legal document pages","author":"Fragkogiannis","year":"2023"},{"key":"10.1016\/j.ipm.2026.105030_b26","series-title":"ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools","author":"GLM","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b27","series-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b28","series-title":"A survey on LLM-as-a-judge","author":"Gu","year":"2025"},{"key":"10.1016\/j.ipm.2026.105030_b29","doi-asserted-by":"crossref","first-page":"44123","DOI":"10.52202\/075280-1915","article-title":"Legalbench: A collaboratively built benchmark for measuring legal reasoning in large language models","volume":"36","author":"Guha","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"8081","key":"10.1016\/j.ipm.2026.105030_b30","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"Deepseek-R1 incentivizes reasoning in LLMs through reinforcement learning","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"issue":"6","key":"10.1016\/j.ipm.2026.105030_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2026.104704","article-title":"Toward better pragmatic tagging of peer review: enhancing benchmark datasets via human-in-the-loop multi-agent collaboration","volume":"63","author":"He","year":"2026","journal-title":"Information Processing & Management"},{"issue":"3","key":"10.1016\/j.ipm.2026.105030_b32","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1093\/ajcl\/avaa018","article-title":"Enforcement of Chinese insider trading law: An empirical and comparative perspective","volume":"68","author":"Huang","year":"2020","journal-title":"The American Journal of Comparative Law"},{"key":"10.1016\/j.ipm.2026.105030_b33","series-title":"Findings of the association for computational linguistics: ACL 2023","first-page":"1049","article-title":"Towards reasoning in large language models: A survey","author":"Huang","year":"2023"},{"key":"10.1016\/j.ipm.2026.105030_b34","series-title":"Lawyer LLaMA technical report","author":"Huang","year":"2023"},{"key":"10.1016\/j.ipm.2026.105030_b35","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","first-page":"16112","article-title":"TKGT: redefinition and a new way of text-to-table tasks based on real world demands and knowledge graphs augmented LLMs","author":"Jiang","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b36","series-title":"Proceedings of the 2025 conference of the nations of the americas chapter of the association for computational linguistics: human language technologies (volume 1: long papers)","first-page":"1153","article-title":"Self-harmonized chain of thought","author":"Jin","year":"2025"},{"key":"10.1016\/j.ipm.2026.105030_b37","series-title":"Proceedings of the 18th conference of the European chapter of the association for computational linguistics: system demonstrations","first-page":"168","article-title":"Meganno+: A human-LLM collaborative annotation system","author":"Kim","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101861","article-title":"ChatGPT: Jack of all trades, master of none","volume":"99","author":"Koco\u0144","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.ipm.2026.105030_b39","doi-asserted-by":"crossref","first-page":"25061","DOI":"10.52202\/079017-0790","article-title":"LexEval: A comprehensive Chinese legal benchmark for evaluating large language models","volume":"37","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.105030_b40","doi-asserted-by":"crossref","unstructured":"Li, M., Shi, T., Ziems, C., Kan, M. Y., Chen, N., Liu, Z. Yang, D. (2023). Coannotating: Uncertainty-guided work allocation between human and large language models for data annotation. In Proceedings of the 2023 conference on empirical methods in natural language processing (pp. 1487\u20131505).","DOI":"10.18653\/v1\/2023.emnlp-main.92"},{"issue":"3","key":"10.1016\/j.ipm.2026.105030_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103996","article-title":"Basis is also explanation: interpretable legal judgment reasoning prompted by multi-source knowledge","volume":"62","author":"Li","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.105030_b42","series-title":"Let\u2019s verify step by step","author":"Lightman","year":"2023"},{"issue":"5","key":"10.1016\/j.ipm.2026.105030_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103796","article-title":"Low-resource court judgment summarization for common law systems","volume":"61","author":"Liu","year":"2024","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.105030_b44","series-title":"Mind your step (by step): Chain-of-thought can reduce performance on tasks where thinking makes humans worse","author":"Liu","year":"2025"},{"key":"10.1016\/j.ipm.2026.105030_b45","series-title":"Law as data: Computation, text, & the future of legal analysis","author":"Livermore","year":"2019"},{"key":"10.1016\/j.ipm.2026.105030_b46","first-page":"22266","article-title":"Interpretable long-form legal question answering with retrieval-augmented large language models","volume":"vol. 38","author":"Louis","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b47","first-page":"32428","article-title":"Large language models struggle with unreasonability in math problems","volume":"vol. 40","author":"Ma","year":"2026"},{"key":"10.1016\/j.ipm.2026.105030_b48","series-title":"The hydra effect: Emergent self-repair in language model computations","author":"McGrath","year":"2023"},{"key":"10.1016\/j.ipm.2026.105030_b49","series-title":"Proceedings of the natural legal language processing workshop 2023","first-page":"73","article-title":"Legal judgment prediction: if you are going to do it, do it right","author":"Medvedeva","year":"2023"},{"issue":"1","key":"10.1016\/j.ipm.2026.105030_b50","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1007\/s10506-021-09306-3","article-title":"Rethinking the field of automatic prediction of court decisions","volume":"31","author":"Medvedeva","year":"2023","journal-title":"Artificial Intelligence and Law"},{"issue":"4","key":"10.1016\/j.ipm.2026.105030_b51","first-page":"501","article-title":"The importance of IRAC and legal writing symposium: advice for prospective law students","volume":"80","author":"Metzler","year":"2003","journal-title":"University of Detroit Mercy Law Review"},{"issue":"2","key":"10.1016\/j.ipm.2026.105030_b52","first-page":"192","article-title":"Meeting the carnegie report\u2019s challenge to make legal analysis explicit-subsidiary skills to the IRAC framework","volume":"59","author":"Miller","year":"2009","journal-title":"Journal of Legal Education"},{"issue":"4","key":"10.1016\/j.ipm.2026.105030_b53","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1007\/s10506-023-09373-8","article-title":"Multi-language transfer learning for low-resource legal case summarization","volume":"32","author":"Moro","year":"2024","journal-title":"Artificial Intelligence and Law"},{"key":"10.1016\/j.ipm.2026.105030_b54","doi-asserted-by":"crossref","first-page":"71876","DOI":"10.1109\/ACCESS.2024.3402809","article-title":"ChatGPT label: comparing the quality of human-generated and LLM-generated annotations in low-resource language NLP tasks","volume":"12","author":"Nasution","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.ipm.2026.105030_b55","doi-asserted-by":"crossref","DOI":"10.1016\/j.clsr.2025.106165","article-title":"LLMs for legal reasoning: A unified framework and future perspectives","volume":"58","author":"Nguyen","year":"2025","journal-title":"Computer Law & Security Review"},{"issue":"1","key":"10.1016\/j.ipm.2026.105030_b56","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103949","article-title":"Retrieve\u2013revise\u2013refine: A novel framework for retrieval of concise entailing legal article set","volume":"62","author":"Nguyen","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.105030_b57","series-title":"Findings of the association for computational linguistics: EMNLP 2023","first-page":"3016","article-title":"LEXTREME: A multi-lingual and multi-task benchmark for the legal domain","author":"Niklaus","year":"2023"},{"key":"10.1016\/j.ipm.2026.105030_b58","series-title":"Show your work: Scratchpads for intermediate computation with language models","author":"Nye","year":"2021"},{"key":"10.1016\/j.ipm.2026.105030_b59","series-title":"GPT-4 technical report","author":"OpenAI","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b60","series-title":"GPT-4o system card","author":"OpenAI","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b61","series-title":"Openai o1 system card","author":"OpenAI","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b62","series-title":"Proceedings of the natural legal language processing workshop 2021","first-page":"9","article-title":"Named entity recognition in the Romanian legal domain","author":"Pais","year":"2021"},{"key":"10.1016\/j.ipm.2026.105030_b63","series-title":"Qwen2.5 technical report","author":"Qwen","year":"2025"},{"issue":"1","key":"10.1016\/j.ipm.2026.105030_b64","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0004-3702(03)00122-X","article-title":"AI and law: A fruitful synergy","volume":"150","author":"Rissland","year":"2003","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.ipm.2026.105030_b65","series-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo","year":"2025"},{"key":"10.1016\/j.ipm.2026.105030_b66","series-title":"A law reasoning benchmark for LLM with tree-organized structures including factum probandum, evidence and experiences","author":"Shen","year":"2025"},{"issue":"1","key":"10.1016\/j.ipm.2026.105030_b67","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/s11196-024-10141-3","article-title":"What is legal reasoning?","volume":"38","author":"Siliquini-Cinelli","year":"2025","journal-title":"International Journal for the Semiotics of Law - Revue Internationale de S\u00e9miotique Juridique"},{"issue":"2","key":"10.1016\/j.ipm.2026.105030_b68","first-page":"511","article-title":"A third view of the black box: cognitive coherence in legal decision making","volume":"71","author":"Simon","year":"2004","journal-title":"The University of Chicago Law Review"},{"issue":"4","key":"10.1016\/j.ipm.2026.105030_b69","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1111\/j.1740-1461.2011.01238.x","article-title":"Lay judgments of judicial decision making","volume":"8","author":"Simon","year":"2011","journal-title":"Journal of Empirical Legal Studies"},{"key":"10.1016\/j.ipm.2026.105030_b70","series-title":"Proceedings of the natural legal language processing workshop 2022","first-page":"305","article-title":"Legal named entity recognition with multi-task domain adaptation","author":"Sm\u0103du","year":"2022"},{"key":"10.1016\/j.ipm.2026.105030_b71","doi-asserted-by":"crossref","DOI":"10.1016\/j.is.2021.101718","article-title":"Multi-label legal document classification: A deep learning-based approach with label-attention and domain-specific pre-training","volume":"106","author":"Song","year":"2022","journal-title":"Information Systems"},{"issue":"2","key":"10.1016\/j.ipm.2026.105030_b72","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/s10506-023-09387-2","article-title":"Discolqa: Zero-shot discourse-based legal question answering on European legislation","volume":"33","author":"Sovrano","year":"2025","journal-title":"Artificial Intelligence and Law"},{"key":"10.1016\/j.ipm.2026.105030_b73","first-page":"94118","article-title":"To cot or not to cot? chain-of-thought helps mainly on math and symbolic reasoning","volume":"vol. 2025","author":"Sprague","year":"2025"},{"issue":"1","key":"10.1016\/j.ipm.2026.105030_b74","first-page":"155","article-title":"If people would be outraged by their rulings, should judges care?","volume":"60","author":"Sunstein","year":"2007","journal-title":"Stanford Law Review"},{"key":"10.1016\/j.ipm.2026.105030_b75","series-title":"Online courts and the future of justice","author":"Susskind","year":"2019"},{"key":"10.1016\/j.ipm.2026.105030_b76","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","first-page":"930","article-title":"Large language models for data annotation and synthesis: A survey","author":"Tan","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b77","series-title":"QwQ-32B: Embracing the power of reinforcement learning","author":"Team","year":"2025"},{"issue":"1","key":"10.1016\/j.ipm.2026.105030_b78","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5296\/ijafr.v3i1.3269","article-title":"A global comparison of insider trading regulations","volume":"3","author":"Thompson","year":"2013","journal-title":"International Journal of Accounting and Financial Reporting"},{"issue":"3","key":"10.1016\/j.ipm.2026.105030_b79","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103663","article-title":"Legal judgment prediction via graph boosting with constraints","volume":"61","author":"Tong","year":"2024","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.105030_b80","series-title":"Proceedings of the 2024 CHI conference on human factors in computing systems","first-page":"1","article-title":"Human-LLM collaborative annotation through effective verification of LLM labels","author":"Wang","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b81","series-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.ipm.2026.105030_b82","doi-asserted-by":"crossref","first-page":"166843","DOI":"10.1109\/ACCESS.2024.3496666","article-title":"LegalReasoner: A multi-stage framework for legal judgment prediction via large language models and knowledge integration","volume":"12","author":"Wang","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.ipm.2026.105030_b83","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.1016\/j.ipm.2026.105030_b84","doi-asserted-by":"crossref","first-page":"279","DOI":"10.2307\/1071994","article-title":"The evolution of reasoned elaboration: jurisprudential criticism and social change","volume":"59","author":"White","year":"1973","journal-title":"Virginia Law Review"},{"key":"10.1016\/j.ipm.2026.105030_b85","first-page":"33944","article-title":"Reasoning or memorization? unreliable results of reinforcement learning due to data contamination","volume":"vol. 40","author":"Wu","year":"2026"},{"issue":"1","key":"10.1016\/j.ipm.2026.105030_b86","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104319","article-title":"A multi-agent framework with legal event logic graph for multi-defendant legal judgment prediction","volume":"63","author":"Yuan","year":"2026","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.105030_b87","series-title":"Automatic chain of thought prompting in large language models","author":"Zhang","year":"2022"},{"key":"10.1016\/j.ipm.2026.105030_b88","series-title":"Proceedings of the 2024 joint international conference on computational linguistics, language resources and evaluation","first-page":"6144","article-title":"Enhancing zero-shot chain-of-thought reasoning in large language models through logic","author":"Zhao","year":"2024"},{"key":"10.1016\/j.ipm.2026.105030_b89","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics","first-page":"5218","article-title":"How does NLP benefit legal system: A summary of legal artificial intelligence","author":"Zhong","year":"2020"},{"key":"10.1016\/j.ipm.2026.105030_b90","series-title":"Don\u2019t make your LLM an evaluation benchmark cheater","author":"Zhou","year":"2023"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326004218?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326004218?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:17:00Z","timestamp":1785910620000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326004218"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":90,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2027,1]]}},"alternative-id":["S0306457326004218"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.105030","relation":{"is-supplemented-by":[{"id-type":"uri","id":"https:\/\/huggingface.co\/datasets\/yuwh07\/mslr-bench","asserted-by":"subject"}]},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Benchmarking multi-step legal reasoning and analyzing Chain-of-Thought effects in Large Language Models","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.105030","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":"105030"}}