{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:44:10Z","timestamp":1774399450929,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP23K28090, JP23K25159"],"award-info":[{"award-number":["JP23K28090, JP23K25159"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730222","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:38:52Z","timestamp":1752457132000},"page":"3035-3039","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["LLM-based Query Expansion Fails for Unfamiliar and Ambiguous Queries"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5413-3158","authenticated-orcid":false,"given":"Kenya","family":"Abe","sequence":"first","affiliation":[{"name":"University of Tsukuba, Tsukuba, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9653-8523","authenticated-orcid":false,"given":"Kunihiro","family":"Takeoka","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9351-0901","authenticated-orcid":false,"given":"Makoto P.","family":"Kato","sequence":"additional","affiliation":[{"name":"University of Tsukuba, Tsukuba, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4045-7350","authenticated-orcid":false,"given":"Masafumi","family":"Oyamada","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Abhijit Anand Vinay Setty Avishek Anand et al. 2023. Context aware query rewriting for text rankers using llm. arXiv preprint arXiv:2308.16753 (2023)."},{"key":"e_1_3_2_1_2_1","first-page":"1609","volume-title":"Companion Proceedings of the ACM on Web Conference","author":"Kruse Ayoub Michael Antonios","year":"2024","unstructured":"Michael Antonios Kruse Ayoub, Zhan Su, and Qiuchi Li. 2024. A Case Study of Enhancing Sparse Retrieval using LLMs. In Companion Proceedings of the ACM on Web Conference 2024. 1609-1615."},{"key":"e_1_3_2_1_3_1","volume-title":"Crafting the path: Robust query rewriting for information retrieval. arXiv preprint arXiv:2407.12529","author":"Baek Ingeol","year":"2024","unstructured":"Ingeol Baek, Jimin Lee, Joonho Yang, and Hwanhee Lee. 2024. Crafting the path: Robust query rewriting for information retrieval. arXiv preprint arXiv:2407.12529 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390377"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2071389.2071390"},{"key":"e_1_3_2_1_6_1","volume-title":"Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael Jordan, Joseph E Gonzalez, et al.","author":"Chiang Wei-Lin","year":"2024","unstructured":"Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael Jordan, Joseph E Gonzalez, et al. 2024. Chatbot arena: An open platform for evaluating llms by human preference. arXiv preprint arXiv:2403.04132 (2024)."},{"key":"e_1_3_2_1_7_1","first-page":"20","volume-title":"Overview of the TREC 2009 Web Track. In Trec","volume":"9","author":"Clarke Charles LA","year":"2009","unstructured":"Charles LA Clarke, Nick Craswell, and Ian Soboroff. 2009. Overview of the TREC 2009 Web Track. In Trec, Vol. 9. 20-29."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671458"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556217"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614949"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_1_12_1","volume-title":"Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118 (2021)."},{"key":"e_1_3_2_1_13_1","volume-title":"Query expansion by prompting large language models. arXiv preprint arXiv:2305.03653","author":"Jagerman Rolf","year":"2023","unstructured":"Rolf Jagerman, Honglei Zhuang, Zhen Qin, Xuanhui Wang, and Michael Bendersky. 2023. Query expansion by prompting large language models. arXiv preprint arXiv:2305.03653 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_15_1","volume-title":"AmbigDocs: Reasoning across Documents on Different Entities under the Same Name. arXiv preprint arXiv:2404.12447","author":"Lee Yoonsang","year":"2024","unstructured":"Yoonsang Lee, Xi Ye, and Eunsol Choi. 2024. AmbigDocs: Reasoning across Documents on Different Entities under the Same Name. arXiv preprint arXiv:2404.12447 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Corpus-Steered Query Expansion with Large Language Models. arXiv preprint arXiv:2402.18031","author":"Lei Yibin","year":"2024","unstructured":"Yibin Lei, Yu Cao, Tianyi Zhou, Tao Shen, and Andrew Yates. 2024. Corpus-Steered Query Expansion with Large Language Models. arXiv preprint arXiv:2402.18031 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28244-7_40"},{"key":"e_1_3_2_1_18_1","volume-title":"Query rewriting for retrieval-augmented large language models. arXiv preprint arXiv:2305.14283","author":"Ma Xinbei","year":"2023","unstructured":"Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, and Nan Duan. 2023. Query rewriting for retrieval-augmented large language models. arXiv preprint arXiv:2305.14283 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591992"},{"key":"e_1_3_2_1_20_1","volume-title":"When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. arXiv preprint arXiv:2212.10511","author":"Mallen Alex","year":"2022","unstructured":"Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. arXiv preprint arXiv:2212.10511 (2022)."},{"key":"e_1_3_2_1_21_1","unstructured":"Meta. 2024. Welcome LLaMA 3 - Meta's new open LLM. https:\/\/github.com\/meta-llama\/llama3. Accessed: 2024-12-20."},{"key":"e_1_3_2_1_22_1","volume-title":"AmbigQA: Answering ambiguous open-domain questions. arXiv preprint arXiv:2004.10645","author":"Min Sewon","year":"2020","unstructured":"Sewon Min, Julian Michael, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2020. AmbigQA: Answering ambiguous open-domain questions. arXiv preprint arXiv:2004.10645 (2020)."},{"key":"e_1_3_2_1_23_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268","author":"Nguyen T","year":"2016","unstructured":"T Nguyen. 2016. MS MARCO: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)."},{"key":"e_1_3_2_1_24_1","unstructured":"OpenAI. 2022. Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt. Accessed: 2024-12-20."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23143"},{"key":"e_1_3_2_1_26_1","volume-title":"James Thorne, Yacine Jernite, Vladimir Karpukhin, Jean Maillard, et al.","author":"Petroni Fabio","year":"2020","unstructured":"Fabio Petroni, Aleksandra Piktus, Angela Fan, Patrick Lewis, Majid Yazdani, Nicola De Cao, James Thorne, Yacine Jernite, Vladimir Karpukhin, Jean Maillard, et al. 2020. KILT: a benchmark for knowledge intensive language tasks. arXiv preprint arXiv:2009.02252 (2020)."},{"key":"e_1_3_2_1_27_1","volume-title":"DEXTER: A Benchmark for open-domain Complex Question Answering using LLMs. arXiv preprint arXiv:2406.17158","author":"Deepali Prabhu Venktesh V","year":"2024","unstructured":"Venktesh V Deepali Prabhu and Avishek Anand. 2024. DEXTER: A Benchmark for open-domain Complex Question Answering using LLMs. arXiv preprint arXiv:2406.17158 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.4630270302"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277756"},{"key":"e_1_3_2_1_30_1","unstructured":"Tetsuya Sakai. 2013. The Unreusability of Diversified Search Test Collections. In EVIA@ NTCIR."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657957"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"George Tsatsaronis Georgios Balikas Prodromos Malakasiotis Ioannis Partalas Matthias Zschunke Michael R Alvers Dirk Weissenborn Anastasia Krithara Sergios Petridis Dimitris Polychronopoulos et al. 2015. An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition. BMC bioinformatics Vol. 16 (2015) 1-28.","DOI":"10.1186\/s12859-015-0564-6"},{"key":"e_1_3_2_1_33_1","unstructured":"Carnegie Mellon University. 2009. ClueWeb09 Dataset. http:\/\/lemurproject.org\/clueweb09\/. Accessed: 2024-12-20."},{"key":"e_1_3_2_1_34_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Cunxiang","year":"2024","unstructured":"Cunxiang Wang, Sirui Cheng, Qipeng Guo, Yuanhao Yue, Bowen Ding, Zhikun Xu, Yidong Wang, Xiangkun Hu, Zheng Zhang, and Yue Zhang. 2024. Evaluating open-qa evaluation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"Query2doc: Query expansion with large language models. arXiv preprint arXiv:2303.07678","author":"Wang Liang","year":"2023","unstructured":"Liang Wang, Nan Yang, and Furu Wei. 2023. Query2doc: Query expansion with large language models. arXiv preprint arXiv:2303.07678 (2023)."},{"key":"e_1_3_2_1_37_1","first-page":"1987","volume-title":"Findings of the Association for Computational Linguistics: EACL 2024","author":"Weller Orion","year":"2024","unstructured":"Orion Weller, Kyle Lo, David Wadden, Dawn Lawrie, Benjamin Van Durme, Arman Cohan, and Luca Soldaini. 2024. When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets. In Findings of the Association for Computational Linguistics: EACL 2024, Yvette Graham and Matthew Purver (Eds.). Association for Computational Linguistics, St. Julian's, Malta, 1987-2003. https:\/\/aclanthology.org\/2024.findings-eacl.134"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679930"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615050"},{"key":"e_1_3_2_1_40_1","volume-title":"CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models. arXiv preprint arXiv:2405.12063","author":"Zhang Tong","year":"2024","unstructured":"Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, and Tat-Seng Chua. 2024. CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models. arXiv preprint arXiv:2405.12063 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Large language models for information retrieval: A survey. arXiv preprint arXiv:2308.07107","author":"Zhu Yutao","year":"2023","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:2308.07107 (2023)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:07:23Z","timestamp":1755864443000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":41,"alternative-id":["10.1145\/3726302.3730222","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730222","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}