{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T07:05:30Z","timestamp":1771571130491,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3770362","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"632-637","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3304-3253","authenticated-orcid":false,"given":"Chanyeol","family":"Choi","sequence":"first","affiliation":[{"name":"LinqAlpha, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2255-7904","authenticated-orcid":false,"given":"Jihoon","family":"Kwon","sequence":"additional","affiliation":[{"name":"LinqAlpha, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5133-7776","authenticated-orcid":false,"given":"Alejandro","family":"Lopez-Lira","sequence":"additional","affiliation":[{"name":"University of Florida, Florida, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4320-8553","authenticated-orcid":false,"given":"Chaewoon","family":"Kim","sequence":"additional","affiliation":[{"name":"LinqAlpha, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3121-2919","authenticated-orcid":false,"given":"Minjae","family":"Kim","sequence":"additional","affiliation":[{"name":"LinqAlpha, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5753-961X","authenticated-orcid":false,"given":"Juneha","family":"Hwang","sequence":"additional","affiliation":[{"name":"LinqAlpha, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3830-7261","authenticated-orcid":false,"given":"Jaeseon","family":"Ha","sequence":"additional","affiliation":[{"name":"LinqAlpha, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2444-1673","authenticated-orcid":false,"given":"Hojun","family":"Choi","sequence":"additional","affiliation":[{"name":"LinqAlpha, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4302-3524","authenticated-orcid":false,"given":"Suyeol","family":"Yun","sequence":"additional","affiliation":[{"name":"LinqAlpha, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8728-6133","authenticated-orcid":false,"given":"Yongjin","family":"Kim","sequence":"additional","affiliation":[{"name":"LinqAlpha, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5411-4340","authenticated-orcid":false,"given":"Yongjae","family":"Lee","sequence":"additional","affiliation":[{"name":"UNIST, Ulsan, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Hongru Cai Yongqi Li Ruifeng Yuan Wenjie Wang Zhen Zhang Wenjie Li and Tat-Seng Chua. 2025. Exploring Training and Inference Scaling Laws in Generative Retrieval. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.18941 (2025)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715490"},{"key":"e_1_3_3_2_4_2","unstructured":"Sanchit Chanana Hyung\u00a0Won Chung Nan Du Jeffrey Zhao et\u00a0al. 2024. Don\u2019t Do RAG: When Cache-Augmented Generation Is All You Need. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.15605 (2024)."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Jaeyoung Choe Jihoon Kim and Woohwan Jung. 2025. Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.20368 (2025).","DOI":"10.18653\/v1\/2025.findings-acl.855"},{"key":"e_1_3_3_2_7_2","unstructured":"Chanyeol Choi Jihoon Kwon Jaeseon Ha Hojun Choi Chaewoon Kim Yongjae Lee Jy yong Sohn and Alejandro Lopez-Lira. 2025. FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.15800 (2025)."},{"key":"e_1_3_3_2_8_2","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yixin Dai Jiawei Sun Haofen Wang and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.10997 2 1 (2023)."},{"key":"e_1_3_3_2_9_2","unstructured":"Pranab Islam Anand Kannappan Douwe Kiela Rebecca Qian Nino Scherrer and Bertie Vidgen. 2023. Financebench: A new benchmark for financial question answering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.11944 (2023)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_3_2_12_2","unstructured":"X Li J Jin Y Zhou Y Zhang P Zhang Y Zhu and Z Dou. [n. d.]. From matching to generation: A survey on generative information retrieval (2024). URL https:\/\/api. semanticscholar. org\/CorpusID 269303210 ([n. d.])."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Yu-An Liu Ruqing Zhang Jiafeng Guo Maarten de Rijke Yixing Fan and Xueqi Cheng. 2024. Robust neural information retrieval: An adversarial and out-of-distribution perspective. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.06992 (2024).","DOI":"10.1145\/3768153"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Kun Luo Minghao Qin Zheng Liu Shitao Xiao Jun Zhao and Kang Liu. 2024. Large language models as foundations for next-gen dense retrieval: A comprehensive empirical assessment. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.12194 (2024).","DOI":"10.18653\/v1\/2024.emnlp-main.80"},{"key":"e_1_3_3_2_15_2","volume-title":"ECIR","author":"Maia Maur\u00edcio\u00a0Sousa","year":"2018","unstructured":"Maur\u00edcio\u00a0Sousa Maia, Alberto H.\u00a0F. Laender, P. Gnther, and Maria da Gra\u00e7a Campos\u00a0Pimentel. 2018. FiQA: A Collection for Aspect-based Opinion Mining and Question Answering. In ECIR."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Mandar Mitra and BB Chaudhuri. 2000. Information retrieval from documents: A survey. Information retrieval 2 (2000) 141\u2013163.","DOI":"10.1023\/A:1009950525500"},{"key":"e_1_3_3_2_17_2","unstructured":"Thong Nguyen and Andrew Yates. 2023. Generative retrieval as dense retrieval. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.11397 (2023)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Joao Palotti Harrisen Scells and Guido Zuccon. 2019. TrecTools: an open-source Python library for Information Retrieval practitioners involved in TREC-like campaigns(SIGIR\u201919). ACM.","DOI":"10.1145\/3331184.3331399"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Ronak Pradeep Kai Hui Jai Gupta Adam\u00a0D Lelkes Honglei Zhuang Jimmy Lin Donald Metzler and Vinh\u00a0Q Tran. 2023. How does generative retrieval scale to millions of passages? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.11841 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.83"},{"key":"e_1_3_3_2_20_2","unstructured":"Varshini Reddy Rik Koncel-Kedziorski Viet\u00a0Dac Lai Michael Krumdick Charles Lovering and Chris Tanner. 2024. Docfinqa: A long-context financial reasoning dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.06915 (2024)."},{"key":"e_1_3_3_2_21_2","first-page":"232","volume-title":"SIGIR","author":"Robertson Stephen\u00a0E.","year":"1994","unstructured":"Stephen\u00a0E. Robertson and Steve Walker. 1994. Some Simple Effective Approximations to the 2\u2010Poisson Model for Probabilistic Weighted Retrieval. In SIGIR. 232\u2013241."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/1096906"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Gerard Salton and Christopher Buckley. 1975. Term\u2010Weighting Approaches in Automatic Text Retrieval. Information Processing & Management 11 5 (1975) 513\u2013523.","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"e_1_3_3_2_24_2","volume-title":"Introduction to information retrieval","author":"Sch\u00fctze Hinrich","year":"2008","unstructured":"Hinrich Sch\u00fctze, Christopher\u00a0D Manning, and Prabhakar Raghavan. 2008. Introduction to information retrieval. Vol.\u00a039. Cambridge University Press Cambridge."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Karen Sparck\u00a0Jones. 1972. A statistical interpretation of term specificity and its application in retrieval. Journal of documentation 28 1 (1972) 11\u201321.","DOI":"10.1108\/eb026526"},{"key":"e_1_3_3_2_26_2","unstructured":"Liang Wang Nan Yang Xiaolong Huang Linjun Yang Rangan Majumder and Furu Wei. 2024. Improving Text Embeddings with Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.00368 (2024)."},{"key":"e_1_3_3_2_27_2","unstructured":"Shunyu Yao Jeffrey Zhao Dian Yu Nan Du Izhak Shafran Karthik Narasimhan and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.03629 (2023)."},{"key":"e_1_3_3_2_28_2","unstructured":"Xiaoju Ye Zhichun Wang and Jingyuan Wang. 2025. Infinite Retrieval: Attention-Enhanced LLMs in Long-Context Processing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.12962 (2025)."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.254"},{"key":"e_1_3_3_2_30_2","unstructured":"Yutao Zhu Huaying Yuan Shuting Wang Jiongnan Liu Wenhan Liu Chenlong Deng Haonan Chen Zheng Liu Zhicheng Dou and Ji-Rong Wen. 2023. Large language models for information retrieval: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.07107 (2023)."}],"event":{"name":"ICAIF '25: 6th ACM International Conference on AI in Finance","location":"Singapore Singapore","acronym":"ICAIF '25"},"container-title":["Proceedings of the 6th ACM International Conference on AI in Finance"],"original-title":[],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:34Z","timestamp":1763105074000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3770362"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":29,"alternative-id":["10.1145\/3768292.3770362","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3770362","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}