{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:29:56Z","timestamp":1768343396126,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,16]]},"DOI":"10.1145\/3769126.3769227","type":"proceedings-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:50:37Z","timestamp":1768315837000},"page":"420-424","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Legal Writing Evaluation of LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0023-1971","authenticated-orcid":false,"given":"Ramon","family":"Pires","sequence":"first","affiliation":[{"name":"Maritaca AI, Campinas, S\u00e3o Paulo, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6005-0515","authenticated-orcid":false,"given":"Roseval","family":"Malaquias Junior","sequence":"additional","affiliation":[{"name":"Maritaca AI, Campinas, S\u00e3o Paulo, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2600-6035","authenticated-orcid":false,"given":"Rodrigo","family":"Nogueira","sequence":"additional","affiliation":[{"name":"Maritaca AI, Campinas, S\u00e3o Paulo, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Hugo Abonizio Thales\u00a0Sales Almeida Thiago Laitz Roseval\u00a0Malaquias Junior Giovana\u00a0Kerche Bon\u00e1s Rodrigo Nogueira and Ramon Pires. 2024. Sabi\u00e1-3 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2410.12049\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2410.12049"},{"key":"e_1_3_3_2_3_2","unstructured":"Anthropic. 2024. Introducing Claude 3.5 Sonnet. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.nllp-1.18"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"e_1_3_3_2_7_2","unstructured":"Pierre Colombo Telmo Pires Malik Boudiaf Rui Melo Dominic Culver Sofia Morgado Etienne Malaboeuf Gabriel Hautreux Johanne Charpentier and Michael Desa. 2024. SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain. arxiv:https:\/\/arXiv.org\/abs\/2407.19584\u00a0[cs.CL]"},{"key":"e_1_3_3_2_8_2","unstructured":"Pierre Colombo Telmo\u00a0Pessoa Pires Malik Boudiaf Dominic Culver Rui Melo Caio Corro Andre F.\u00a0T. Martins Fabrizio Esposito Vera\u00a0L\u00facia Raposo Sofia Morgado and Michael Desa. 2024. SaulLM-7B: A pioneering Large Language Model for Law. arxiv:https:\/\/arXiv.org\/abs\/2403.03883\u00a0[cs.CL]"},{"key":"e_1_3_3_2_9_2","volume-title":"Recurso Personalizado para 2\u00aa Fase OAB 41\u00ba Exame","author":"Ordem Prova da","year":"2025","unstructured":"Prova da Ordem. 2025. Recurso Personalizado para 2\u00aa Fase OAB 41\u00ba Exame. https:\/\/www.provadaordem.com.br\/produto\/recursos-personalizados-2a-fase\/"},{"key":"e_1_3_3_2_10_2","unstructured":"DeepSeek-AI and Daya\u00a0Guo et al. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2501.12948\u00a0[cs.CL]"},{"key":"e_1_3_3_2_11_2","unstructured":"Yann Dubois Bal\u00e1zs Galambosi Percy Liang and Tatsunori\u00a0B. Hashimoto. 2024. Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators. arxiv:https:\/\/arXiv.org\/abs\/2404.04475\u00a0[cs.LG]"},{"key":"e_1_3_3_2_12_2","unstructured":"Zhiwei Fei Xiaoyu Shen Dawei Zhu Fengzhe Zhou Zhuo Han Songyang Zhang Kai Chen Zongwen Shen and Jidong Ge. 2023. LawBench: Benchmarking Legal Knowledge of Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2309.16289\u00a0[cs.CL]"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"e_1_3_3_2_14_2","unstructured":"Elliot Glazer Ege Erdil Tamay Besiroglu Diego Chicharro Evan Chen Alex Gunning Caroline\u00a0Falkman Olsson Jean-Stanislas Denain Anson Ho Emily de\u00a0Oliveira Santos et\u00a0al. 2024. Frontiermath: A benchmark for evaluating advanced mathematical reasoning in ai. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.04872 (2024)."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4583531"},{"key":"e_1_3_3_2_16_2","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. arxiv:https:\/\/arXiv.org\/abs\/2009.03300\u00a0[cs.CY]"},{"key":"e_1_3_3_2_17_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jimenez Carlos\u00a0E","year":"2024","unstructured":"Carlos\u00a0E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik\u00a0R Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-world Github Issues?. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=VTF8yNQM66"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Atsushi Mizumoto and Masaki Eguchi. 2023. Exploring the potential of using an AI language model for automated essay scoring. Research Methods in Applied Linguistics 2 2 (2023) 100050.","DOI":"10.1016\/j.rmal.2023.100050"},{"key":"e_1_3_3_2_20_2","unstructured":"OpenAI. 2024. Introducing OpenAI o1. https:\/\/openai.com\/o1\/. Accessed: 26 January 2025."},{"key":"e_1_3_3_2_21_2","unstructured":"OpenAI and Aaron\u00a0Hurst et al. 2024. GPT-4o System Card. (2024). arxiv:https:\/\/arXiv.org\/abs\/2410.21276\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_3_2_22_2","unstructured":"OpenAI and Aaron\u00a0Jaech et al. 2024. OpenAI o1 System Card. (2024). arxiv:https:\/\/arXiv.org\/abs\/2412.16720\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2412.16720"},{"key":"e_1_3_3_2_23_2","unstructured":"Qwen and An\u00a0Yang et al. 2025. Qwen2.5 Technical Report. (2025). arxiv:https:\/\/arXiv.org\/abs\/2412.15115\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_3_2_24_2","unstructured":"David Rein Betty\u00a0Li Hou Asa\u00a0Cooper Stickland Jackson Petty Richard\u00a0Yuanzhe Pang Julien Dirani Julian Michael and Samuel\u00a0R. Bowman. 2023. GPQA: A Graduate-Level Google-Proof Q&A Benchmark. arxiv:https:\/\/arXiv.org\/abs\/2311.12022\u00a0[cs.AI]"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nllp-1.13"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.511"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bea-1.49"},{"key":"e_1_3_3_2_28_2","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et\u00a0al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems 36 (2023) 46595\u201346623."}],"event":{"name":"ICAIL 2025: 20th International Conference on Artificial Intelligence and Law","location":"Chicago , IL , USA","acronym":"ICAIL 2025"},"container-title":["Proceedings of the Twentieth International Conference on Artificial Intelligence and Law"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3769126.3769227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:47:46Z","timestamp":1768319266000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769126.3769227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,16]]},"references-count":27,"alternative-id":["10.1145\/3769126.3769227","10.1145\/3769126"],"URL":"https:\/\/doi.org\/10.1145\/3769126.3769227","relation":{},"subject":[],"published":{"date-parts":[[2025,6,16]]},"assertion":[{"value":"2026-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}