{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T17:24:41Z","timestamp":1776792281294,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","funder":[{"name":"Ministry of Science and ICT, South Korea","award":["IITP-2022(2025)-RS-2022-00156435"],"award-info":[{"award-number":["IITP-2022(2025)-RS-2022-00156435"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761151","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:29:28Z","timestamp":1762561768000},"page":"1396-1405","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Where Does Legal AI Fail? Evaluating RAG Pipelines"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0216-2687","authenticated-orcid":false,"given":"Yongjae","family":"Kim","sequence":"first","affiliation":[{"name":"The Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9584-2101","authenticated-orcid":false,"given":"Wonjae","family":"Lee","sequence":"additional","affiliation":[{"name":"The Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Jianlv Chen Shitao Xiao Peitian Zhang Kun Luo Defu Lian and Zheng Liu. 2024. BGE M3-Embedding: Multi-Lingual Multi-Functionality Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. arXiv:2402.03216 [cs.CL]","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657834"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/jla\/laae003"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar Maria Lomeli Lucas Hosseini and Herv Jgou. 2024. The Faiss library. (2024). arXiv:2401.08281 [cs.LG]","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"e_1_3_2_2_5_1","unstructured":"Grant C. Forbes Parth Katlana and Zeydy Ortiz. 2023. Metric Ensembles For Hallucination Detection. arXiv:2310.10495 [cs.CL] https:\/\/arxiv.org\/abs\/2310. 10495"},{"key":"e_1_3_2_2_6_1","volume-title":"Ankita Rajaram Naik, Pengshan Cai, and Alfio Gliozzo.","author":"Glass Michael","year":"2022","unstructured":"Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Ankita Rajaram Naik, Pengshan Cai, and Alfio Gliozzo. 2022. Re2G: Retrieve, Rerank, Generate. arXiv:2207.06300 [cs.CL] https:\/\/arxiv.org\/abs\/2207.06300"},{"key":"e_1_3_2_2_7_1","volume-title":"REALM: Retrieval-Augmented Language Model Pre-Training. arXiv:2002.08909 [cs.CL] https:\/\/arxiv.org\/abs\/2002.08909","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. REALM: Retrieval-Augmented Language Model Pre-Training. arXiv:2002.08909 [cs.CL] https:\/\/arxiv.org\/abs\/2002.08909"},{"key":"e_1_3_2_2_8_1","volume-title":"RAGGED: Towards Informed Design of Retrieval Augmented Generation Systems. arXiv:2403.09040 [cs.CL] https:\/\/arxiv.org\/abs\/2403.09040","author":"Hsia Jennifer","year":"2024","unstructured":"Jennifer Hsia, Afreen Shaikh, Zhiruo Wang, and Graham Neubig. 2024. RAGGED: Towards Informed Design of Retrieval Augmented Generation Systems. arXiv:2403.09040 [cs.CL] https:\/\/arxiv.org\/abs\/2403.09040"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Omar Khattab and Matei Zaharia. 2020. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. arXiv:2004.12832 [cs.IR] https:\/\/arxiv.org\/abs\/2004.12832","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_2_11_1","volume-title":"Tim Rocktschel, Sebastian Riedel, and Douwe Kiela.","author":"Lewis Patrick","year":"2021","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Kttler, Mike Lewis, Wen tau Yih, Tim Rocktschel, Sebastian Riedel, and Douwe Kiela. 2021. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv:2005.11401 [cs.CL] https:\/\/arxiv.org\/abs\/2005.11401"},{"key":"e_1_3_2_2_12_1","unstructured":"Chaofan Li Zheng Liu Shitao Xiao and Yingxia Shao. 2023. Making Large Language Models A Better Foundation For Dense Retrieval. arXiv:2312.15503 [cs.CL]"},{"key":"e_1_3_2_2_13_1","unstructured":"Jiarui Li Ye Yuan and Zehua Zhang. 2024. Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases. arXiv:2403.10446 [cs.CL] https:\/\/arxiv.org\/abs\/2403.10446"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.20362"},{"key":"e_1_3_2_2_15_1","unstructured":"Chandana Sree Mala Gizem Gezici and Fosca Giannotti. 2025. Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis. arXiv:2504.05324 [cs.IR] https:\/\/arxiv.org\/abs\/2504.05324"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Joshua Maynez Shashi Narayan Bernd Bohnet and Ryan McDonald. 2020. On Faithfulness and Factuality in Abstractive Summarization. arXiv:2005.00661 [cs.CL] https:\/\/arxiv.org\/abs\/2005.00661","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Sewon Min Kalpesh Krishna Xinxi Lyu Mike Lewis Wen tau Yih PangWei Koh Mohit Iyyer Luke Zettlemoyer and Hannaneh Hajishirzi. 2023. FActScore: Finegrained Atomic Evaluation of Factual Precision in Long Form Text Generation. arXiv:2305.14251 [cs.CL] https:\/\/arxiv.org\/abs\/2305.14251","DOI":"10.18653\/v1\/2023.emnlp-main.741"},{"key":"e_1_3_2_2_18_1","unstructured":"Nicholas Pipitone and Ghita Houir Alami. 2024. LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain. arXiv:2408.10343 [cs.AI] https:\/\/arxiv.org\/abs\/2408.10343"},{"key":"e_1_3_2_2_19_1","volume-title":"Series of Large Language Models for Realworld Use Cases. arXiv preprint arXiv:https:\/\/arxiv.org\/abs\/2412.04862","author":"Research LG AI","year":"2024","unstructured":"LG AI Research. 2024. EXAONE 3.5: Series of Large Language Models for Realworld Use Cases. arXiv preprint arXiv:https:\/\/arxiv.org\/abs\/2412.04862 (2024)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nllp-1.13"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Shamane Siriwardhana Rivindu Weerasekera Elliott Wen Tharindu Kaluarachchi Rajib Rana and Suranga Nanayakkara. 2022. Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering. arXiv:2210.02627 [cs.CL] https:\/\/arxiv.org\/abs\/2210.02627","DOI":"10.1162\/tacl_a_00530"},{"key":"e_1_3_2_2_22_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric P. Xing Hao Zhang Joseph E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. arXiv:2306.05685 [cs.CL] https:\/\/arxiv.org\/abs\/2306.05685"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:52:46Z","timestamp":1765504366000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":22,"alternative-id":["10.1145\/3746252.3761151","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761151","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}