{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T00:34:05Z","timestamp":1792197245380,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,3]]},"DOI":"10.1145\/3788646.3789522","type":"proceedings-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:48:12Z","timestamp":1779479292000},"page":"71-85","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0375-1793","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computing and Information, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6586-2486","authenticated-orcid":false,"given":"Matthias","family":"Grabmair","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Bavaria, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3800-2103","authenticated-orcid":false,"given":"Morgan","family":"Gray","sequence":"additional","affiliation":[{"name":"School of Computing and Information, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5535-0759","authenticated-orcid":false,"given":"Kevin","family":"Ashley","sequence":"additional","affiliation":[{"name":"School of Computing and Information, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1057\/s41599-024-04044-8"},{"key":"e_1_3_2_1_2_1","unstructured":"Sandhini Agarwal Lama Ahmad Jason Ai Sam Altman Andy Applebaum Edwin Arbus Rahul K Arora Yu Bai Bowen Baker Haiming Bao et al. 2025. gpt-oss-120b & gpt-oss-20b model card. arXiv preprint arXiv:2508.10925 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Predicting judicial decisions of the European Court of Human Rights: A natural language processing perspective. PeerJ computer science 2","author":"Aletras Nikolaos","year":"2016","unstructured":"Nikolaos Aletras, Dimitrios Tsarapatsanis, Daniel Preo\u0163iuc-Pietro, and Vasileios Lampos. 2016. Predicting judicial decisions of the European Court of Human Rights: A natural language processing perspective. PeerJ computer science 2 (2016), e93."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/222092.222106"},{"key":"e_1_3_2_1_5_1","volume-title":"Teaching case-based argumentation through a model and examples","author":"Aleven Vincent AWMM","unstructured":"Vincent AWMM Aleven. 1997. Teaching case-based argumentation through a model and examples. University of Pittsburgh."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-7373(91)90011-U"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114920"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1017\/9781316761380"},{"key":"e_1_3_2_1_9_1","unstructured":"Kevin D Ashley and Vincent Aleven. 1997. Reasoning symbolically about partially matched cases. In IJCAI (1). 335\u2013341."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law. 12\u201321","author":"Atkinson Katie","year":"2019","unstructured":"Katie Atkinson and Trevor Bench-Capon. 2019. Reasoning with legal cases: Analogy or rule application?. In Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law. 12\u201321."},{"key":"e_1_3_2_1_11_1","volume-title":"Llms for explainable ai: A comprehensive survey. arXiv preprint arXiv:2504.00125","author":"Bilal Ahsan","year":"2025","unstructured":"Ahsan Bilal, David Ebert, and Beiyu Lin. 2025. Llms for explainable ai: A comprehensive survey. arXiv preprint arXiv:2504.00125 (2025)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1047788.1047838"},{"key":"e_1_3_2_1_13_1","volume-title":"An alignment safety case sketch based on debate. arXiv preprint arXiv:2505.03989","author":"Buhl Marie Davidsen","year":"2025","unstructured":"Marie Davidsen Buhl, Jacob Pfau, Benjamin Hilton, and Geoffrey Irving. 2025. An alignment safety case sketch based on debate. arXiv preprint arXiv:2505.03989 (2025)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3594536.3595148"},{"key":"e_1_3_2_1_15_1","volume-title":"Obligation and prohibition extraction using hierarchical RNNs. arXiv preprint arXiv:1805.03871","author":"Chalkidis Ilias","year":"2018","unstructured":"Ilias Chalkidis, Ion Androutsopoulos, and Achilleas Michos. 2018. Obligation and prohibition extraction using hierarchical RNNs. arXiv preprint arXiv:1805.03871 (2018)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Bao Kham Chau and Michael A Livermore. 2024. Computational legal studies comes of age. (2024).","DOI":"10.62355\/ejels.19684"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622073"},{"key":"e_1_3_2_1_18_1","volume-title":"Computational Models of Argument","author":"Collenette Joe","unstructured":"Joe Collenette, Katie Atkinson, and Trevor Bench-Capon. 2020. An explainable approach to deducing outcomes in European Court of Human Rights cases using ADFs. In Computational Models of Argument. IOS Press, 21\u201332."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103861"},{"key":"e_1_3_2_1_20_1","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et al. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning multi-modality long context and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","first-page":"735","DOI":"10.2307\/1119147","article-title":"Stare decisis","volume":"49","author":"Douglas William O","year":"1949","unstructured":"William O Douglas. 1949. Stare decisis. Columbia Law Review 49, 6 (1949), 735\u2013758.","journal-title":"Columbia Law Review"},{"key":"e_1_3_2_1_22_1","volume-title":"The power of precedent","author":"Gerhardt Michael J","unstructured":"Michael J Gerhardt. 2011. The power of precedent. Oxford University Press."},{"key":"e_1_3_2_1_23_1","volume-title":"Mi-Young Kim, and Masaharu Yoshioka.","author":"Goebel Randy","year":"2025","unstructured":"Randy Goebel, Yoshinobu Kano, Japan Calum Kawn, Mi-Young Kim, and Masaharu Yoshioka. 2025. International Competition on Legal Information Extraction and Entailment (COLIEE 2025). (2025)."},{"key":"e_1_3_2_1_24_1","volume-title":"Modeling purposive legal argumentation and case outcome prediction using argument schemes in the value judgment formalism. Ph. D. Dissertation","author":"Grabmair Matthias","unstructured":"Matthias Grabmair. 2016. Modeling purposive legal argumentation and case outcome prediction using argument schemes in the value judgment formalism. Ph. D. Dissertation. University of Pittsburgh."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3086512.3086521"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709025.3712216"},{"key":"e_1_3_2_1_27_1","volume-title":"Brandon Waldon, Daniel Rockmore, Diego Zambrano, et al.","author":"Guha Neel","year":"2023","unstructured":"Neel Guha, Julian Nyarko, Daniel Ho, Christopher R\u00e9, Adam Chilton, Alex Chohlas-Wood, Austin Peters, Brandon Waldon, Daniel Rockmore, Diego Zambrano, et al. 2023. Legalbench: A collaboratively built benchmark for measuring legal reasoning in large language models. Advances in neural information processing systems 36 (2023), 44123\u201344279."},{"key":"e_1_3_2_1_28_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_29_1","volume-title":"Cuad: An expert-annotated nlp dataset for legal contract review. arXiv preprint arXiv:2103.06268","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Anya Chen, and Spencer Ball. 2021. Cuad: An expert-annotated nlp dataset for legal contract review. arXiv preprint arXiv:2103.06268 (2021)."},{"key":"e_1_3_2_1_30_1","volume-title":"Rules and reasons in the theory of precedent. Legal theory 17, 1","author":"Horty John F","year":"2011","unstructured":"John F Horty. 2011. Rules and reasons in the theory of precedent. Legal theory 17, 1 (2011), 1\u201333."},{"key":"e_1_3_2_1_31_1","unstructured":"Evan Hubinger Carson Denison Jesse Mu Mike Lambert Meg Tong Monte MacDiarmid Tamera Lanham Daniel M Ziegler Tim Maxwell Newton Cheng et al. 2024. Sleeper agents: Training deceptive llms that persist through safety training. arXiv preprint arXiv:2401.05566 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"AI safety via debate. arXiv preprint arXiv:1805.00899","author":"Irving Geoffrey","year":"2018","unstructured":"Geoffrey Irving, Paul Christiano, and Dario Amodei. 2018. AI safety via debate. arXiv preprint arXiv:1805.00899 (2018)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clsr.2024.106053"},{"key":"e_1_3_2_1_34_1","volume-title":"Do Xuan Long, Minzhi Li, Chengwei Qin, Peifeng Wang, Silvio Savarese, et al.","author":"Ke Zixuan","year":"2025","unstructured":"Zixuan Ke, Fangkai Jiao, Yifei Ming, Xuan-Phi Nguyen, Austin Xu, Do Xuan Long, Minzhi Li, Chengwei Qin, Peifeng Wang, Silvio Savarese, et al. 2025. A survey of frontiers in llm reasoning: Inference scaling, learning to reason, and agentic systems. arXiv preprint arXiv:2504.09037 (2025)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3086512.3086550"},{"key":"e_1_3_2_1_36_1","unstructured":"Grant Lamond. 2006. Precedent and analogy in legal reasoning. (2006)."},{"key":"e_1_3_2_1_37_1","volume-title":"Multi-defendant legal judgment prediction via hierarchical reasoning. arXiv preprint arXiv:2312.05762","author":"Lyu Yougang","year":"2023","unstructured":"Yougang Lyu, Jitai Hao, Zihan Wang, Kai Zhao, Shen Gao, Pengjie Ren, Zhumin Chen, Fang Wang, and Zhaochun Ren. 2023. Multi-defendant legal judgment prediction via hierarchical reasoning. arXiv preprint arXiv:2312.05762 (2023)."},{"key":"e_1_3_2_1_38_1","unstructured":"Gr\u00e9goire Mialon Roberto Dess\u00ec Maria Lomeli Christoforos Nalmpantis Ram Pasunuru Roberta Raileanu Baptiste Rozi\u00e8re Timo Schick Jane Dwivedi-Yu Asli Celikyilmaz et al. 2023. Augmented language models: a survey. arXiv preprint arXiv:2302.07842 (2023)."},{"key":"e_1_3_2_1_39_1","unstructured":"OpenAI. 2025. GPT-5 System Card. https:\/\/cdn.openai.com\/gpt-5-system-card.pdf. Accessed on 2025-08-26."},{"key":"e_1_3_2_1_40_1","volume-title":"Judge AI: Assessing large language models in judicial decision-making","author":"Posner Eric A","year":"2025","unstructured":"Eric A Posner and Shivam Saran. 2025. Judge AI: Assessing large language models in judicial decision-making. University of Chicago Coase-Sandor Institute for Law & Economics Research Paper 2503 (2025)."},{"key":"e_1_3_2_1_41_1","unstructured":"Qwen Team. 2025. Qwen3-235B-A22B-Instruct-2507-FP8. https:\/\/huggingface.co\/unsloth\/Qwen3-235B-A22B-Instruct-2507-GGUF"},{"key":"e_1_3_2_1_42_1","unstructured":"Qwen Team. 2025. Qwen3-235B-A22B-Thinking-2507-FP8. https:\/\/huggingface.co\/Qwen\/Qwen3-235B-A22B-Thinking-2507-FP8"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-7373(91)90013-W"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1111\/j.1745-6924.2008.00090.x","article-title":"Why precedent in law (and elsewhere) is not totally (or even substantially) about analogy","volume":"3","author":"Schauer Frederick","year":"2008","unstructured":"Frederick Schauer. 2008. Why precedent in law (and elsewhere) is not totally (or even substantially) about analogy. Perspectives on Psychological Science 3, 6 (2008), 454\u2013460.","journal-title":"Perspectives on Psychological Science"},{"key":"e_1_3_2_1_45_1","volume-title":"expertise, and experience","author":"Schauer Frederick","year":"2017","unstructured":"Frederick Schauer and Barbara A Spellman. 2017. Analogy, expertise, and experience. The University of Chicago Law Review (2017), 249\u2013268."},{"key":"e_1_3_2_1_46_1","volume-title":"AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction. arXiv preprint arXiv:2503.00128","author":"Sesodia Magnus","year":"2025","unstructured":"Magnus Sesodia, Alina Petrova, John Armour, Thomas Lukasiewicz, Oana-Maria Camburu, Puneet K Dokania, Philip Torr, and Christian Schroeder de Witt. 2025. AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction. arXiv preprint arXiv:2503.00128 (2025)."},{"key":"e_1_3_2_1_47_1","first-page":"587","article-title":"History as Precedent: Common Law Reasoning in Historical Investigation","volume":"27","author":"Smith Michael L","year":"2025","unstructured":"Michael L Smith. 2025. History as Precedent: Common Law Reasoning in Historical Investigation. University of Pennsylvania Journal of Constitutional Law 27, 3 (2025), 587.","journal-title":"University of Pennsylvania Journal of Constitutional Law"},{"key":"e_1_3_2_1_48_1","unstructured":"Unsloth AI. 2025. gpt-oss: How to Run & Fine-tune. https:\/\/docs.unsloth.ai\/new\/gpt-oss-how-to-run-and-fine-tune#running-gpt-oss"},{"key":"e_1_3_2_1_49_1","volume-title":"Hierarchical Reasoning Model. arXiv preprint arXiv:2506.21734","author":"Wang Guan","year":"2025","unstructured":"Guan Wang, Jin Li, Yuhao Sun, Xing Chen, Changling Liu, Yue Wu, Meng Lu, Sen Song, and Yasin Abbasi Yadkori. 2025. Hierarchical Reasoning Model. arXiv preprint arXiv:2506.21734 (2025)."},{"key":"e_1_3_2_1_50_1","unstructured":"Peng-Yuan Wang Tian-Shuo Liu Chenyang Wang Yi-Di Wang Shu Yan Cheng-Xing Jia Xu-Hui Liu Xin-Wei Chen Jia-Cheng Xu Ziniu Li et al. 2025. A Survey on Large Language Models for Mathematical Reasoning. arXiv preprint arXiv:2506.08446 (2025)."},{"key":"e_1_3_2_1_51_1","volume-title":"Plangenllms: A modern survey of llm planning capabilities. arXiv preprint arXiv:2502.11221","author":"Wei Hui","year":"2025","unstructured":"Hui Wei, Zihao Zhang, Shenghua He, Tian Xia, Shijia Pan, and Fei Liu. 2025. Plangenllms: A modern survey of llm planning capabilities. arXiv preprint arXiv:2502.11221 (2025)."},{"key":"e_1_3_2_1_52_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022), 24824\u201324837."},{"key":"e_1_3_2_1_53_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_54_1","volume-title":"Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems 36","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems 36 (2023), 11809\u201311822."},{"key":"e_1_3_2_1_55_1","volume-title":"Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation. arXiv preprint arXiv:2506.02992","author":"Zhang Li","year":"2025","unstructured":"Li Zhang and Kevin D Ashley. 2025. Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation. arXiv preprint arXiv:2506.02992 (2025)."},{"key":"e_1_3_2_1_56_1","volume-title":"Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments. arXiv preprint arXiv:2506.00694","author":"Zhang Li","year":"2025","unstructured":"Li Zhang, Morgan Gray, Jaromir Savelka, and Kevin D Ashley. 2025. Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments. arXiv preprint arXiv:2506.00694 (2025)."}],"event":{"name":"CSLAW '26: Symposium on Computer Science and Law","location":"Berkeley CA USA","acronym":"CSLAW '26","sponsor":["ACM Association for Computing Machinery"]},"container-title":["Proceedings of the Symposium on Computer Science and Law"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788646.3789522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:48:43Z","timestamp":1779479323000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788646.3789522"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,3]]},"references-count":56,"alternative-id":["10.1145\/3788646.3789522","10.1145\/3788646"],"URL":"https:\/\/doi.org\/10.1145\/3788646.3789522","relation":{},"subject":[],"published":{"date-parts":[[2026,3,3]]},"assertion":[{"value":"2026-05-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}