{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:38:08Z","timestamp":1783737488411,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Youth Innovation Promotion Association CAS","award":["2021100"],"award-info":[{"award-number":["2021100"]}]},{"name":"Strategic Priority Research Program of the CAS","award":["No. XDB0680102"],"award-info":[{"award-number":["No. XDB0680102"]}]},{"name":"LESSEN","award":["NWA.1389.20.183"],"award-info":[{"award-number":["NWA.1389.20.183"]}]},{"name":"FINDHR","award":["101070212"],"award-info":[{"award-number":["101070212"]}]},{"name":"Lenovo-CAS Joint Lab Youth Scientist Project","award":["JCKY2022130C039"],"award-info":[{"award-number":["JCKY2022130C039"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFA1011602; 2021QY1701"],"award-info":[{"award-number":["2023YFA1011602; 2021QY1701"]}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["62372431"],"award-info":[{"award-number":["62372431"]}]},{"name":"10-year"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657784","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1941-1951","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Are Large Language Models Good at Utility Judgments?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1144-1298","authenticated-orcid":false,"given":"Hengran","family":"Zhang","sequence":"first","affiliation":[{"name":"CAS Key Lab of Network Data Science and Technology, ICT, CAS &amp; University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4294-2541","authenticated-orcid":false,"given":"Ruqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"CAS Key Lab of Network Data Science and Technology, ICT, CAS &amp; University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-8674","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[{"name":"CAS Key Lab of Network Data Science and Technology, ICT, CAS &amp; University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-0202","authenticated-orcid":false,"given":"Maarten","family":"de Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4317-2702","authenticated-orcid":false,"given":"Yixing","family":"Fan","sequence":"additional","affiliation":[{"name":"CAS Key Lab of Network Data Science and Technology, ICT, CAS &amp; University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5201-8195","authenticated-orcid":false,"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"CAS Key Lab of Network Data Science and Technology, ICT, CAS &amp; University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Ahmad Aghaebrahimian. 2018. Linguistically-based Deep Unstructured Question Answering. CoNLL 433--443.","DOI":"10.18653\/v1\/K18-1042"},{"key":"e_1_3_2_1_2_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with ChatGPT Quality. https:\/\/vicuna.lmsys.org (Accessed 14 April 2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Mean Reciprocal Rank. Encyclopedia of Database Systems 1703","author":"Craswell Nick","year":"2009","unstructured":"Nick Craswell. 2009. Mean Reciprocal Rank. Encyclopedia of Database Systems 1703 (2009)."},{"key":"e_1_3_2_1_4_1","volume-title":"Gianluca Demartini, Matthias Hagen, Claudia Hauff, Noriko Kando, Evangelos Kanoulas, Martin Potthast, Benno Stein, et al.","author":"Faggioli Guglielmo","year":"2023","unstructured":"Guglielmo Faggioli, Laura Dietz, Charles LA Clarke, Gianluca Demartini, Matthias Hagen, Claudia Hauff, Noriko Kando, Evangelos Kanoulas, Martin Potthast, Benno Stein, et al. 2023. Perspectives on Large Language Models for Relevance Judgment. In SIGIR. 39--50."},{"key":"e_1_3_2_1_5_1","volume-title":"RIGHT: Retrieval-Augmented Generation for Mainstream Hashtag Recommendation. In European Conference on Information Retrieval. Springer, 39--55","author":"Fan Run-Ze","year":"2024","unstructured":"Run-Ze Fan, Yixing Fan, Jiangui Chen, Jiafeng Guo, Ruqing Zhang, and Xueqi Cheng. 2024. RIGHT: Retrieval-Augmented Generation for Mainstream Hashtag Recommendation. In European Conference on Information Retrieval. Springer, 39--55."},{"key":"e_1_3_2_1_6_1","volume-title":"arXiv preprint arXiv:2402.12219","author":"Fan Run-Ze","year":"2024","unstructured":"Run-Ze Fan, Xuefeng Li, Haoyang Zou, Junlong Li, Shwai He, Ethan Chern, Jiewen Hu, and Pengfei Liu. 2024. Reformatted Alignment. arXiv preprint arXiv:2402.12219 (2024). https:\/\/arxiv.org\/abs\/2402.12219"},{"key":"e_1_3_2_1_7_1","volume-title":"ANTIQUE: A Non-factoid Question Answering Benchmark. In ECIR","author":"Hashemi Helia","year":"2020","unstructured":"Helia Hashemi, Mohammad Aliannejadi, Hamed Zamani, and W Bruce Croft. 2020. ANTIQUE: A Non-factoid Question Answering Benchmark. In ECIR 2020. Springer, 166--173."},{"key":"e_1_3_2_1_8_1","unstructured":"Pengcheng He Xiaodong Liu Jianfeng Gao and Weizhu Chen. 2021. DeBERTa: Decoding-enhanced BERT with Disentangled Attention. In ICLR."},{"key":"e_1_3_2_1_9_1","unstructured":"Matthew Honnibal. 2017. spaCy. (2017). https:\/\/spacy.io\/"},{"key":"e_1_3_2_1_10_1","volume-title":"Large Language Models are Zero-shot Rankers for Recommender Systems. arXiv preprint arXiv:2305.08845","author":"Hou Yupeng","year":"2023","unstructured":"Yupeng Hou, Junjie Zhang, Zihan Lin, Hongyu Lu, Ruobing Xie, Julian McAuley, and Wayne Xin Zhao. 2023. Large Language Models are Zero-shot Rankers for Recommender Systems. arXiv preprint arXiv:2305.08845 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. EACL","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard and Edouard Grave. 2021. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. EACL (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Few-shot Learning with Retrieval Augmented Language Models. arXiv preprint arXiv:2208.03299","author":"Izacard Gautier","year":"2022","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022. Few-shot Learning with Retrieval Augmented Language Models. arXiv preprint arXiv:2208.03299 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130348.3130374"},{"key":"e_1_3_2_1_14_1","volume-title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion. ACL","author":"Jiang Dongfu","year":"2023","unstructured":"Dongfu Jiang, Xiang Ren, and Bill Yuchen Lin. 2023. LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion. ACL (2023)."},{"key":"e_1_3_2_1_15_1","first-page":"22199","article-title":"Large Language Models are Zero-shot Reasoners","volume":"35","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large Language Models are Zero-shot Reasoners. NeurIPS 35 (2022), 22199--22213.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_17_1","first-page":"9459","article-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. NeurIPS 33 (2020), 9459--9474.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_18_1","volume-title":"Self-alignment with instruction backtranslation. arXiv preprint arXiv:2308.06259","author":"Li Xian","year":"2023","unstructured":"Xian Li, Ping Yu, Chunting Zhou, Timo Schick, Luke Zettlemoyer, Omer Levy, Jason Weston, and Mike Lewis. 2023. Self-alignment with instruction backtranslation. arXiv preprint arXiv:2308.06259 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Rouge: A Package for Automatic Evaluation of Summaries. In Text summarization branches out. 74--81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A Package for Automatic Evaluation of Summaries. In Text summarization branches out. 74--81."},{"key":"e_1_3_2_1_20_1","volume-title":"WebGLM: Towards An EfficientWeb-Enhanced Question Answering System with Human Preferences. KDD","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Hanyu Lai, Hao Yu, Yifan Xu, Aohan Zeng, Zhengxiao Du, Peng Zhang, Yuxiao Dong, and Jie Tang. 2023. WebGLM: Towards An EfficientWeb-Enhanced Question Answering System with Human Preferences. KDD (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614793"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1700--1709","author":"Liu Yu-An","year":"2023","unstructured":"Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Yixing Fan, and Xueqi Cheng. 2023. Topic-oriented Adversarial Attacks against Blackbox Neural Ranking Models. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1700--1709."},{"key":"e_1_3_2_1_23_1","volume-title":"Entity-based Knowledge Conflicts in Question Answering. EMNLP","author":"Longpre Shayne","year":"2021","unstructured":"Shayne Longpre, Kartik Perisetla, Anthony Chen, Nikhil Ramesh, Chris DuBois, and Sameer Singh. 2021. Entity-based Knowledge Conflicts in Question Answering. EMNLP (2021)."},{"key":"e_1_3_2_1_24_1","volume-title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity. ACL","author":"Lu Yao","year":"2022","unstructured":"Yao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel, and Pontus Stenetorp. 2022. Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity. ACL (2022)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Alex Mallen Akari Asai Victor Zhong Rajarshi Das Daniel Khashabi and Hannaneh Hajishirzi. 2023. When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-parametric Memories. In ACL. 9802--9822.","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"e_1_3_2_1_26_1","volume-title":"MS MARCO: A Human Generated Machine Reading Comprehension Dataset. choice 2640","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A Human Generated Machine Reading Comprehension Dataset. choice 2640 (2016), 660."},{"key":"e_1_3_2_1_27_1","volume-title":"When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation. arXiv preprint arXiv:2402.11457","author":"Ni Shiyu","year":"2024","unstructured":"Shiyu Ni, Keping Bi, Jiafeng Guo, and Xueqi Cheng. 2024. When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation. arXiv preprint arXiv:2402.11457 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085 (2019)."},{"key":"e_1_3_2_1_29_1","volume-title":"openai.com\/blog\/chatgpt","author":"Introducing AI.","year":"2022","unstructured":"OpenAI. 2022. Introducing ChatGPT. (2022). openai.com\/blog\/chatgpt."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Kishore Papineni Salim Roukos Todd Ward and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In ACL. 311--318.","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_31_1","volume-title":"Large language models sensitivity to the order of options in multiple-choice questions. arXiv preprint arXiv:2308.11483","author":"Pezeshkpour Pouya","year":"2023","unstructured":"Pouya Pezeshkpour and Estevam Hruschka. 2023. Large language models sensitivity to the order of options in multiple-choice questions. arXiv preprint arXiv:2308.11483 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models. arXiv preprint arXiv:2309.15088","author":"Pradeep Ronak","year":"2023","unstructured":"Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023. RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models. arXiv preprint arXiv:2309.15088 (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Zhen Qin Rolf Jagerman Kai Hui Honglei Zhuang Junru Wu Jiaming Shen Tianqi Liu Jialu Liu Donald Metzler Xuanhui Wang et al. 2023. Large Language Models are Effective Text Rankers with Pairwise Ranking prompting. arXiv preprint arXiv:2306.17563 (2023).","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"e_1_3_2_1_34_1","volume-title":"In-Context Retrieval-Augmented Language Models. TACL","author":"Ram Ori","year":"2023","unstructured":"Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. In-Context Retrieval-Augmented Language Models. TACL (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Qiaoqiao She, Hua Wu, Haifeng Wang, and Ji-Rong Wen.","author":"Ren Ruiyang","year":"2021","unstructured":"Ruiyang Ren, Yingqi Qu, Jing Liu, Wayne Xin Zhao, Qiaoqiao She, Hua Wu, Haifeng Wang, and Ji-Rong Wen. 2021. RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking. EMNLP (2021)."},{"key":"e_1_3_2_1_36_1","volume-title":"Jing Liu, Hao Tian, Hua Wu, Ji-Rong Wen, and Haifeng Wang.","author":"Ren Ruiyang","year":"2023","unstructured":"Ruiyang Ren, Yuhao Wang, Yingqi Qu, Wayne Xin Zhao, Jing Liu, Hao Tian, Hua Wu, Ji-Rong Wen, and Haifeng Wang. 2023. Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation. arXiv preprint arXiv:2307.11019 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Tefko Saracevic. 2016. The Notion of Relevance in Information Science: Everybody knows what relevance is. But what is it really? Morgan & Claypool Publishers.","DOI":"10.1007\/978-3-031-02302-6"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(198805)39:3<161::AID-ASI2>3.0.CO;2-0"},{"key":"e_1_3_2_1_39_1","volume-title":"REPLUG: Retrieval-augmented Black-box Language Models. arXiv preprint arXiv:2301.12652","author":"Shi Weijia","year":"2023","unstructured":"Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2023. REPLUG: Retrieval-augmented Black-box Language Models. arXiv preprint arXiv:2301.12652 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Retrieval Augmentation Reduces Hallucination in Conversation. arXiv preprint arXiv:2104.07567","author":"Shuster Kurt","year":"2021","unstructured":"Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval Augmentation Reduces Hallucination in Conversation. arXiv preprint arXiv:2104.07567 (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. EMNLP","author":"Sun Weiwei","year":"2023","unstructured":"Weiwei Sun, Lingyong Yan, Xinyu Ma, Pengjie Ren, Dawei Yin, and Zhaochun Ren. 2023. Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. EMNLP (2023)."},{"key":"e_1_3_2_1_42_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.524"},{"key":"e_1_3_2_1_44_1","first-page":"24824","article-title":"Chain-of-thought Prompting Elicits Reasoning in Large Language Models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. Chain-of-thought Prompting Elicits Reasoning in Large Language Models. NeurIPS 35 (2022), 24824--24837.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469856"},{"key":"e_1_3_2_1_46_1","volume-title":"Adaptive Chameleon or Stubborn Sloth: Unraveling the Behavior of Large Language Models in Knowledge Conflicts. arXiv preprint arXiv:2305.13300","author":"Xie Jian","year":"2023","unstructured":"Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou, and Yu Su. 2023. Adaptive Chameleon or Stubborn Sloth: Unraveling the Behavior of Large Language Models in Knowledge Conflicts. arXiv preprint arXiv:2305.13300 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26618"},{"key":"e_1_3_2_1_48_1","volume-title":"Manning","author":"Yang Zhilin","year":"2018","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, WilliamW. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. ACL (2018)."},{"key":"e_1_3_2_1_49_1","volume-title":"Generate Rather than Retrieve: Large Language Models are Strong Context Generators. ICLR","author":"Yu Wenhao","year":"2023","unstructured":"Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, and Meng Jiang. 2023. Generate Rather than Retrieve: Large Language Models are Strong Context Generators. ICLR (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Hamed Zamani Fernando Diaz Mostafa Dehghani Donald Metzler and Michael Bendersky. 2022. Retrieval-enhanced Machine Learning. In SIGIR. 2875--2886.","DOI":"10.1145\/3477495.3531722"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Jingtao Zhan Jiaxin Mao Yiqun Liu Jiafeng Guo Min Zhang and Shaoping Ma. 2021. Optimizing Dense Retrieval Model Training with Hard Negatives. In SIGIR. 1503--1512.","DOI":"10.1145\/3404835.3462880"},{"key":"e_1_3_2_1_52_1","volume-title":"From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification. EMNLP Findings","author":"Zhang Hengran","year":"2023","unstructured":"Hengran Zhang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, and Xueqi Cheng. 2023. From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification. EMNLP Findings (2023)."},{"key":"e_1_3_2_1_53_1","volume-title":"Hybrid Retrieval-Augmented Generation for Real-time Composition Assistance. arXiv preprint arXiv:2308.04215","author":"Zhang Xuchao","year":"2023","unstructured":"Xuchao Zhang, Menglin Xia, Camille Couturier, Guoqing Zheng, Saravan Rajmohan, and Victor Ruhle. 2023. Hybrid Retrieval-Augmented Generation for Real-time Composition Assistance. arXiv preprint arXiv:2308.04215 (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Beyond Yes and No: Improving Zero-shot LLM Rankers via Scoring Fine-grained Relevance Labels. arXiv preprint arXiv:2310.14122","author":"Zhuang Honglei","year":"2023","unstructured":"Honglei Zhuang, Zhen Qin, Kai Hui, Junru Wu, Le Yan, Xuanhui Wang, and Michael Berdersky. 2023. Beyond Yes and No: Improving Zero-shot LLM Rankers via Scoring Fine-grained Relevance Labels. arXiv preprint arXiv:2310.14122 (2023)."},{"key":"e_1_3_2_1_55_1","volume-title":"A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models. arXiv preprint arXiv:2310.09497","author":"Zhuang Shengyao","year":"2023","unstructured":"Shengyao Zhuang, Honglei Zhuang, Bevan Koopman, and Guido Zuccon. 2023. A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models. arXiv preprint arXiv:2310.09497 (2023)."}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657784","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:40:34Z","timestamp":1755841234000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657784"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":55,"alternative-id":["10.1145\/3626772.3657784","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657784","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}