{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:21:33Z","timestamp":1784092893344,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,18]]},"DOI":"10.1145\/3731120.3744609","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T13:34:06Z","timestamp":1752845646000},"page":"401-409","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring the Utility of Embedding Similarity for Contract Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2938-328X","authenticated-orcid":false,"given":"Jonathan","family":"Donnelly","sequence":"first","affiliation":[{"name":"Zuva Inc, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1265-8881","authenticated-orcid":false,"given":"Adam","family":"Roegiest","sequence":"additional","affiliation":[{"name":"Zuva Inc, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944937"},{"key":"e_1_3_2_1_2_1","volume-title":"Enriching Word Vectors with Subword Information. arXiv preprint arXiv:1607.04606","author":"Bojanowski Piotr","year":"2016","unstructured":"Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2016. Enriching Word Vectors with Subword Information. arXiv preprint arXiv:1607.04606 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2537734.2537742"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2051"},{"key":"e_1_3_2_1_6_1","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. (2024). arxiv:2401.08281 [cs.LG]"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '88)","author":"Dumais S. T.","unstructured":"S. T. Dumais, G. W. Furnas, T. K. Landauer, S. Deerwester, and R. Harshman. 1988. Using latent semantic analysis to improve access to textual information. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '88)."},{"key":"e_1_3_2_1_8_1","volume-title":"Data Eng.","volume":"13","author":"Faloutsos C.","year":"1990","unstructured":"C. Faloutsos. 1990. Signature-based Text Retrieval Methods: A Survey. Data Eng., Vol. 13, 1 (1990)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664190.3672511"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148222"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_12_1","unstructured":"Antonios Minas Krasakis Andrew Yates and Evangelos Kanoulas. 2025. Constructing Set-Compositional and Negated Representations for First-Stage Ranking. arxiv:2501.07679 [cs.IR] https:\/\/arxiv.org\/abs\/2501.07679"},{"key":"e_1_3_2_1_13_1","unstructured":"Chankyu Lee Rajarshi Roy Mengyao Xu Jonathan Raiman Mohammad Shoeybi Bryan Catanzaro and Wei Ping. 2025. NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models. arxiv:2405.17428 [cs.CL] https:\/\/arxiv.org\/abs\/2405.17428"},{"key":"e_1_3_2_1_14_1","volume-title":"Gustavo Hernandez Abrego, Weiqiang Shi, Nithi Gupta, Aditya Kusupati, Prateek Jain, Siddhartha Reddy Jonnalagadda, Ming-Wei Chang, and Iftekhar Naim.","author":"Lee Jinhyuk","year":"2024","unstructured":"Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren, Blair Chen, Daniel Cer, Jeremy R. Cole, Kai Hui, Michael Boratko, Rajvi Kapadia, Wen Ding, Yi Luan, Sai Meher Karthik Duddu, Gustavo Hernandez Abrego, Weiqiang Shi, Nithi Gupta, Aditya Kusupati, Prateek Jain, Siddhartha Reddy Jonnalagadda, Ming-Wei Chang, and Iftekhar Naim. 2024. Gecko: Versatile Text Embeddings Distilled from Large Language Models. arxiv:2403.20327 [cs.CL] https:\/\/arxiv.org\/abs\/2403.20327"},{"key":"e_1_3_2_1_15_1","unstructured":"Spyretta Leivaditi Julien Rossi and Evangelos Kanoulas. 2020. A Benchmark for Lease Contract Review. arxiv:2010.10386 [cs.IR] https:\/\/arxiv.org\/abs\/2010.10386"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2348283.2348471"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505706"},{"key":"e_1_3_2_1_18_1","unstructured":"Nelson F. Liu Kevin Lin John Hewitt Ashwin Paranjape Michele Bevilacqua Fabio Petroni and Percy Liang. 2023. Lost in the Middle: How Language Models Use Long Contexts. arxiv:2307.03172 [cs.CL] https:\/\/arxiv.org\/abs\/2307.03172"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000016"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615112"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482013"},{"key":"e_1_3_2_1_22_1","unstructured":"Tomas Mikolov Kai Chen Greg Corrado and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. arxiv:1301.3781 [cs.CL] https:\/\/arxiv.org\/abs\/1301.3781"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.741"},{"key":"e_1_3_2_1_24_1","unstructured":"Arvind Neelakantan Tao Xu Raul Puri Alec Radford Jesse Michael Han Jerry Tworek Qiming Yuan Nikolas Tezak Jong Wook Kim Chris Hallacy Johannes Heidecke Pranav Shyam Boris Power Tyna Eloundou Nekoul Girish Sastry Gretchen Krueger David Schnurr Felipe Petroski Such Kenny Hsu Madeleine Thompson Tabarak Khan Toki Sherbakov Joanne Jang Peter Welinder and Lilian Weng. 2022. Text and Code Embeddings by Contrastive Pre-Training. arxiv:2201.10005 [cs.CL] https:\/\/arxiv.org\/abs\/2201.10005"},{"key":"e_1_3_2_1_25_1","unstructured":"Adam Roegiest and Radha Chitta. 2024. Answering Questions in Stages: Prompt Chaining for Contract QA. arxiv:2410.12840 [cs.CL] https:\/\/arxiv.org\/abs\/2410.12840"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331311"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 2022 Conference of the North American","author":"Santhanam Keshav","unstructured":"Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, and Matei Zaharia. 2022. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Marine Carpuat, Marie-Catherine de Marneffe, and Ivan Vladimir Meza Ruiz (Eds.). Association for Computational Linguistics, Seattle, United States, 3715-3734."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.5162111"},{"key":"e_1_3_2_1_29_1","volume-title":"Soft Similarity and Soft Cosine Measure: Similarity of Features in Vector Space Model. Computaci\u00f3n y Sistemas","author":"Sidorov Grigori","year":"2014","unstructured":"Grigori Sidorov, Alexander Gelbukh, Helena G\u00f3mez-Adorno, and David Pinto. 2014. Soft Similarity and Soft Cosine Measure: Similarity of Features in Vector Space Model. Computaci\u00f3n y Sistemas, Vol. 18 (2014)."},{"key":"e_1_3_2_1_30_1","unstructured":"ValsAI. [n.d.]. Vals Legal AI Report. https:\/\/www.vals.ai\/vlair."},{"key":"e_1_3_2_1_31_1","unstructured":"Coen van den Elsen Francien Barkhof Thijmen Nijdam Simon Lupart and Mohammad Alliannejadi. 2025. Reproducing NevIR: Negation in Neural Information Retrieval. arxiv:2502.13506 [cs.IR] https:\/\/arxiv.org\/abs\/2502.13506"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2662145"},{"key":"e_1_3_2_1_33_1","volume-title":"Eliminating Position Bias of Language Models: A Mechanistic Approach. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=fvkElsJOsN","author":"Wang Ziqi","year":"2025","unstructured":"Ziqi Wang, Hanlin Zhang, Xiner Li, Kuan-Hao Huang, Chi Han, Shuiwang Ji, Sham M. Kakade, Hao Peng, and Heng Ji. 2025. Eliminating Position Bias of Language Models: A Mechanistic Approach. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=fvkElsJOsN"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.139"},{"key":"e_1_3_2_1_35_1","unstructured":"Yijiong Yu Huiqiang Jiang Xufang Luo Qianhui Wu Chin-Yew Lin Dongsheng Li Yuqing Yang Yongfeng Huang and Lili Qiu. 2024. Mitigate Position Bias in Large Language Models via Scaling a Single Dimension. arxiv:2406.02536 [cs.CL] https:\/\/arxiv.org\/abs\/2406.02536"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835455"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609600"}],"event":{"name":"ICTIR '25: International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval","location":"Padua Italy","acronym":"ICTIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731120.3744609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:18:57Z","timestamp":1755868737000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731120.3744609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":37,"alternative-id":["10.1145\/3731120.3744609","10.1145\/3731120"],"URL":"https:\/\/doi.org\/10.1145\/3731120.3744609","relation":{},"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}