{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:32:27Z","timestamp":1768343547638,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,16]]},"DOI":"10.1145\/3769126.3769205","type":"proceedings-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:50:37Z","timestamp":1768315837000},"page":"114-128","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessing the performance gap between lexical and semantic models for information retrieval with formulaic legal language"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4321-0403","authenticated-orcid":false,"given":"Larissa","family":"Mori","sequence":"first","affiliation":[{"name":"Edwardson School of Industrial Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8834-1385","authenticated-orcid":false,"given":"Carlos","family":"Sousa de Oliveira","sequence":"additional","affiliation":[{"name":"Edwardson School of Industrial Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2087-7718","authenticated-orcid":false,"given":"Yuehwern","family":"Yih","sequence":"additional","affiliation":[{"name":"Edwardson School of Industrial Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1246-297X","authenticated-orcid":false,"given":"Mario","family":"Ventresca","sequence":"additional","affiliation":[{"name":"Edwardson School of Industrial Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocab":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Loic Azoulai. 2011. The retained powers\u2019 formula in the case law of the European Court of Justice: EU law as total law. Eur. J. Legal Stud. 4 (2011) 178. Publisher: HeinOnline."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. 10.48550\/arXiv.1810.04805arXiv:https:\/\/arXiv.org\/abs\/1810.04805 [cs].","DOI":"10.48550\/arXiv.1810.04805"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.350"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3594536.3595176"},{"key":"e_1_3_3_2_8_2","unstructured":"Matthew Henderson Rami Al-Rfou Brian Strope Yun-hsuan Sung Laszlo Lukacs Ruiqi Guo Sanjiv Kumar Balint Miklos and Ray Kurzweil. 2017. Efficient Natural Language Response Suggestion for Smart Reply. http:\/\/arxiv.org\/abs\/1705.00652 arXiv:https:\/\/arXiv.org\/abs\/1705.00652 [cs]."},{"key":"e_1_3_3_2_9_2","unstructured":"Abe\u00a0Bohan Hou Orion Weller Guanghui Qin Eugene Yang Dawn Lawrie Nils Holzenberger Andrew Blair-Stanek and Benjamin Van\u00a0Durme. 2024. CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation. http:\/\/arxiv.org\/abs\/2406.17186 arXiv:https:\/\/arXiv.org\/abs\/2406.17186 [cs]."},{"key":"e_1_3_3_2_10_2","unstructured":"Jeff Johnson Matthijs Douze and Herv\u00e9 J\u00e9gou. 2017. Billion-scale similarity search with GPUs. http:\/\/arxiv.org\/abs\/1702.08734 arXiv:https:\/\/arXiv.org\/abs\/1702.08734 [cs]."},{"key":"e_1_3_3_2_11_2","unstructured":"Vladimir Karpukhin Barlas O\u011fuz Sewon Min Patrick Lewis Ledell Wu Sergey Edunov Danqi Chen and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. http:\/\/arxiv.org\/abs\/2004.04906 arXiv:https:\/\/arXiv.org\/abs\/2004.04906 [cs]."},{"key":"e_1_3_3_2_12_2","unstructured":"Kenton Lee Ming-Wei Chang and Kristina Toutanova. 2019. Latent retrieval for weakly supervised open domain question answering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.00300 (2019)."},{"key":"e_1_3_3_2_13_2","unstructured":"Daniel Locke and Guido Zuccon. 2022. Case law retrieval: problems methods challenges and evaluations in the last 20 years. http:\/\/arxiv.org\/abs\/2202.07209 arXiv:https:\/\/arXiv.org\/abs\/2202.07209 [cs]."},{"key":"e_1_3_3_2_14_2","unstructured":"Robert Mahari Dominik Stammbach Elliott Ash and Alex\u00a0\u2018Sandy\u2019 Pentland. 2023. LePaRD: A Large-Scale Dataset of Judges Citing Precedents. http:\/\/arxiv.org\/abs\/2311.09356 arXiv:https:\/\/arXiv.org\/abs\/2311.09356 [cs]."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Enys Mones Piotr Sapie\u017cy\u0144ski Simon Thordal Henrik\u00a0Palmer Olsen and Sune Lehmann. 2021. Emergence of network effects and predictability in the judicial system. Scientific Reports 11 1 (Feb. 2021) 2740. 10.1038\/s41598-021-82430-x","DOI":"10.1038\/s41598-021-82430-x"},{"key":"e_1_3_3_2_16_2","unstructured":"Zach Nussbaum John\u00a0X. Morris Brandon Duderstadt and Andriy Mulyar. 2024. Nomic embed: Training a reproducible long context text embedder. arXiv:https:\/\/arXiv.org\/abs\/2402.01613 [cs.CL]."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230982"},{"key":"e_1_3_3_2_18_2","first-page":"59","volume-title":"Legal knowledge and information systems","author":"Panagis Yannis","year":"2017","unstructured":"Yannis Panagis, Ur\u0161ka \u0160adl, and Fabien Tarissan. 2017. Giving every case its (legal) due-the contribution of citation networks and text similarity techniques to legal studies of European Union law. In Legal knowledge and information systems. IOS Press, 59\u201368."},{"key":"e_1_3_3_2_19_2","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. http:\/\/arxiv.org\/abs\/1908.10084 arXiv:https:\/\/arXiv.org\/abs\/1908.10084 [cs]."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Stephen Robertson Hugo Zaragoza and others. 2009. The probabilistic relevance framework: BM25 and beyond. Foundations and Trends\u00ae in Information Retrieval 3 4 (2009) 333\u2013389.","DOI":"10.1561\/1500000019"},{"key":"e_1_3_3_2_21_2","unstructured":"Guilherme\u00a0Moraes Rosa Ruan\u00a0Chaves Rodrigues Roberto Lotufo and Rodrigo Nogueira. 2021. Yes BM25 is a Strong Baseline for Legal Case Retrieval. http:\/\/arxiv.org\/abs\/2105.05686 arXiv:https:\/\/arXiv.org\/abs\/2105.05686 [cs]."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.nllp-1.12"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315445724-6"},{"key":"e_1_3_3_2_24_2","first-page":"5473","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"T.y.s.s. Santosh","year":"2024","unstructured":"Santosh T.y.s.s., Rashid Haddad, and Matthias Grabmair. 2024. ECtHR-PCR: A Dataset for Precedent Understanding and Prior Case Retrieval in the European Court of Human Rights. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, Torino, Italia, 5473\u20135483. https:\/\/aclanthology.org\/2024.lrec-main.486"}],"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\/3769126.3769205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:49:53Z","timestamp":1768319393000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769126.3769205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,16]]},"references-count":23,"alternative-id":["10.1145\/3769126.3769205","10.1145\/3769126"],"URL":"https:\/\/doi.org\/10.1145\/3769126.3769205","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"}}]}}