{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:23:47Z","timestamp":1764782627990,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62206042"],"award-info":[{"award-number":["62206042"]}]},{"name":"Fundamental Research Funds for the Central Universities","award":["N25ZLL045"],"award-info":[{"award-number":["N25ZLL045"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,7]]},"DOI":"10.1145\/3767695.3769491","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:14:58Z","timestamp":1764782098000},"page":"292-302","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7594-3132","authenticated-orcid":false,"given":"Yifan","family":"Ji","sequence":"first","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3671-5978","authenticated-orcid":false,"given":"Zhipeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0083-3224","authenticated-orcid":false,"given":"Zhenghao","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2421-7098","authenticated-orcid":false,"given":"Yukun","family":"Yan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6335-1076","authenticated-orcid":false,"given":"Shi","family":"Yu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2837-1358","authenticated-orcid":false,"given":"Yishan","family":"Li","sequence":"additional","affiliation":[{"name":"ModelBest Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7709-2543","authenticated-orcid":false,"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7422-6254","authenticated-orcid":false,"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3171-8889","authenticated-orcid":false,"given":"Ge","family":"Yu","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6011-6115","authenticated-orcid":false,"given":"Maosong","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. ArXiv preprint abs\/2303.08774 (2023). https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_2_1","volume-title":"Guilherme Penedo, Lewis Tunstall, Andr\u00e9s Marafioti, Hynek Kydl\u00ed\u010dek, Agust\u00edn Piqueres Lajar\u00edn, Vaibhav Srivastav, Joshua Lochner, Caleb Fahlgren, et al.","author":"Allal Loubna Ben","year":"2025","unstructured":"Loubna Ben Allal, Anton Lozhkov, Elie Bakouch, Gabriel Mart\u00edn Bl\u00e1zquez, Guilherme Penedo, Lewis Tunstall, Andr\u00e9s Marafioti, Hynek Kydl\u00ed\u010dek, Agust\u00edn Piqueres Lajar\u00edn, Vaibhav Srivastav, Joshua Lochner, Caleb Fahlgren, et al., 2025. SmolLM2: When Smol Goes Big - Data-Centric Training of a Small Language Model. ArXiv preprint abs\/2502.02737 (2025). https:\/\/arxiv.org\/abs\/2502.02737"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.225"},{"key":"e_1_3_2_1_4_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. ArXiv preprint abs\/1611.09268","author":"Bajaj Payal","year":"2016","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2016. MS MARCO: A human generated machine reading comprehension dataset. ArXiv preprint abs\/1611.09268 (2016). https:\/\/arxiv.org\/abs\/1611.09268"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of COLM. https:\/\/openreview.net\/forum?id=IW1PR7vEBf","author":"BehnamGhader Parishad","year":"2024","unstructured":"Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, and Siva Reddy. 2024. LLM2Vec: Large language models are secretly powerful text encoders. In Proceedings of COLM. https:\/\/openreview.net\/forum?id=IW1PR7vEBf"},{"key":"e_1_3_2_1_6_1","first-page":"34","article-title":"Open-domain question answering","author":"Chen Danqi","year":"2020","unstructured":"Danqi Chen and Wen-tau Yih. 2020. Open-domain question answering. In Proceedings of ACL. 34-37. https:\/\/aclanthology.org\/2020.acl-tutorials.8","journal-title":"Proceedings of ACL."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3648327"},{"key":"e_1_3_2_1_8_1","volume-title":"Cohen","author":"Chen Wenhu","year":"2023","unstructured":"Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W. Cohen. 2023. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. Transactions on Machine Learning Research (2023). https:\/\/openreview.net\/forum?id=YfZ4ZPt8zd"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.65"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of NeurIPS. 16344-16359","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. FlashAttention: Fast and memory-efficient exact attention with io-awareness. In Proceedings of NeurIPS. 16344-16359. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/67d57c32e20fd0a7a302cb81d36e40d5-Paper-Conference.pdf"},{"key":"e_1_3_2_1_11_1","volume-title":"Lili Jiang, Meg Risdal, Nikhil Dandekar, and tomtung.","year":"2017","unstructured":"DataCanary, hilfialkaff, Lili Jiang, Meg Risdal, Nikhil Dandekar, and tomtung. 2017. Quora question pairs. https:\/\/kaggle.com\/competitions\/quora-question-pairs. Kaggle."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1346"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.99"},{"key":"e_1_3_2_1_14_1","first-page":"6894","article-title":"SimCSE: Simple contrastive learning of sentence embeddings","author":"Gao Tianyu","year":"2021","unstructured":"Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. SimCSE: Simple contrastive learning of sentence embeddings. In Proceedings of EMNLP. 6894-6910. https:\/\/aclanthology.org\/2021.emnlp-main.552\/","journal-title":"Proceedings of EMNLP."},{"key":"e_1_3_2_1_15_1","first-page":"3929","article-title":"Retrieval augmented language model pre-training","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In Proceedings of ICML. 3929-3938. https:\/\/proceedings.mlr.press\/v119\/guu20a.html","journal-title":"Proceedings of ICML."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210065"},{"key":"e_1_3_2_1_17_1","volume-title":"Training large language models to reason in a continuous latent space. ArXiv preprint abs\/2412.06769","author":"Hao Shibo","year":"2024","unstructured":"Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, and Yuandong Tian. 2024. Training large language models to reason in a continuous latent space. ArXiv preprint abs\/2412.06769 (2024). https:\/\/arxiv.org\/abs\/2412.06769"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2605"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of ICLR. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In Proceedings of ICLR. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of COLM. https:\/\/openreview.net\/forum?id=3X2L2TFr0f","author":"Hu Shengding","year":"2024","unstructured":"Shengding Hu, Yuge Tu, Xu Han, Ganqu Cui, Chaoqun He, Weilin Zhao, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Xinrong Zhang, Zhen Leng Thai, Chongyi Wang, Yuan Yao, Chenyang Zhao, Jie Zhou, Jie Cai, Zhongwu Zhai, Ning Ding, Chao Jia, Guoyang Zeng, dahai li, Zhiyuan Liu, and Maosong Sun. 2024. MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies. In Proceedings of COLM. https:\/\/openreview.net\/forum?id=3X2L2TFr0f"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_3_2_1_22_1","first-page":"6769","article-title":"Dense passage retrieval for open-domain question answering","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. In Proceedings of EMNLP. 6769-6781. https:\/\/aclanthology.org\/2020.emnlp-main.550","journal-title":"Proceedings of EMNLP."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657798"},{"key":"e_1_3_2_1_25_1","volume-title":"Think-to-talk or talk-to-think? When llms come up with an answer in multi-step reasoning. ArXiv preprint abs\/2412.01113","author":"Kudo Keito","year":"2024","unstructured":"Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi, Shusaku Sone, Masaya Taniguchi, Ana Brassard, Keisuke Sakaguchi, and Kentaro Inui. 2024. Think-to-talk or talk-to-think? When llms come up with an answer in multi-step reasoning. ArXiv preprint abs\/2412.01113 (2024). https:\/\/arxiv.org\/abs\/2412.01113"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_27_1","volume-title":"Gecko: Versatile text embeddings distilled from large language models. ArXiv preprint abs\/2403.20327","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, et al., 2024. Gecko: Versatile text embeddings distilled from large language models. ArXiv preprint abs\/2403.20327 (2024). https:\/\/arxiv.org\/abs\/2403.20327"},{"key":"e_1_3_2_1_28_1","first-page":"3490","article-title":"Llama2vec: Unsupervised adaptation of large language models for dense retrieval","author":"Li Chaofan","year":"2024","unstructured":"Chaofan Li, Zheng Liu, Shitao Xiao, Yingxia Shao, and Defu Lian. 2024. Llama2vec: Unsupervised adaptation of large language models for dense retrieval. In Proceedings of ACL. 3490-3500. https:\/\/aclanthology.org\/2024.acl-long.191\/","journal-title":"Proceedings of ACL."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of ICLR. https:\/\/openreview.net\/forum?id=wfLuiDjQ0u","author":"Li Chaofan","year":"2025","unstructured":"Chaofan Li, Minghao Qin, Shitao Xiao, Jianlyu Chen, Kun Luo, Yingxia Shao, Defu Lian, and Zheng Liu. 2025. Making text embedders few-shot learners. In Proceedings of ICLR. https:\/\/openreview.net\/forum?id=wfLuiDjQ0u"},{"key":"e_1_3_2_1_30_1","first-page":"7342","article-title":"Fine-grained fact verification with kernel graph attention network","author":"Liu Zhenghao","year":"2020","unstructured":"Zhenghao Liu, Chenyan Xiong, Maosong Sun, and Zhiyuan Liu. 2020. Fine-grained fact verification with kernel graph attention network. In Proceedings of ACL. 7342-7351. https:\/\/aclanthology.org\/2020.acl-main.655","journal-title":"Proceedings of ACL."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.80"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_33_1","volume-title":"Sgpt: Gpt sentence embeddings for semantic search. ArXiv preprint abs\/2202.08904","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff. 2022. Sgpt: Gpt sentence embeddings for semantic search. ArXiv preprint abs\/2202.08904 (2022). https:\/\/arxiv.org\/abs\/2202.08904"},{"key":"e_1_3_2_1_34_1","volume-title":"Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al.","author":"Neelakantan Arvind","year":"2022","unstructured":"Arvind Neelakantan, Tao Xu, Raul Puri, Alec Radford, Jesse Michael Han, Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al., 2022. Text and code embeddings by contrastive pre-training. ArXiv preprint abs\/2201.10005 (2022). https:\/\/arxiv.org\/abs\/2201.10005"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.669"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of ICLR. https:\/\/openreview.net\/forum?id=Ahlrf2HGJR","author":"Springer Jacob Mitchell","year":"2025","unstructured":"Jacob Mitchell Springer, Suhas Kotha, Daniel Fried, Graham Neubig, and Aditi Raghunathan. 2025. Repetition improves language model embeddings. In Proceedings of ICLR. https:\/\/openreview.net\/forum?id=Ahlrf2HGJR"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.71"},{"key":"e_1_3_2_1_39_1","volume-title":"LLMs are also effective embedding models: An in-depth overview. ArXiv preprint abs\/2412.12591","author":"Tao Chongyang","year":"2024","unstructured":"Chongyang Tao, Tao Shen, Shen Gao, Junshuo Zhang, Zhen Li, Zhengwei Tao, and Shuai Ma. 2024. LLMs are also effective embedding models: An in-depth overview. ArXiv preprint abs\/2412.12591 (2024). https:\/\/arxiv.org\/abs\/2412.12591"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of NeurIPS. https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A heterogeneous benchmark for zero-shot evaluation of information retrieval models. In Proceedings of NeurIPS. https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1074"},{"key":"e_1_3_2_1_42_1","volume-title":"Llama: Open and efficient foundation language models. ArXiv preprint abs\/2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. ArXiv preprint abs\/2302.13971 (2023). https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.642"},{"key":"e_1_3_2_1_44_1","volume-title":"Multilingual e5 text embeddings: A technical report. ArXiv preprint abs\/2402.05672","author":"Wang Liang","year":"2024","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024b. Multilingual e5 text embeddings: A technical report. ArXiv preprint abs\/2402.05672 (2024). https:\/\/arxiv.org\/abs\/2402.05672"},{"key":"e_1_3_2_1_45_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022a. Emergent abilities of large language models. ArXiv preprint abs\/2206.07682 (2022). https:\/\/arxiv.org\/abs\/2206.07682"},{"key":"e_1_3_2_1_46_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022b. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/9d5609613524ecf4f15af0f7b31abca4-Paper-Conference.pdf"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591874"},{"key":"e_1_3_2_1_48_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xie Yuxi","year":"2024","unstructured":"Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, James Xu Zhao, Min-Yen Kan, Junxian He, and Michael Xie. 2024. Self-evaluation guided beam search for reasoning. Advances in Neural Information Processing Systems, Vol. 36 (2024). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/81fde95c4dc79188a69ce5b24d63010b-Paper-Conference.pdf"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of ICLR. https:\/\/openreview.net\/forum?id=zeFrfgyZln","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In Proceedings of ICLR. https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"e_1_3_2_1_50_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei Huan Lin Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jingren Zhou Junyang Lin Kai Dang Keming Lu et al. 2025. Qwen2.5 Technical Report. ArXiv preprint abs\/2412.15115 (2025). https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_51_1","first-page":"2369","article-title":"HotpotQA: A dataset for diverse, explainable multi-hop question answering","author":"Yang Zhilin","year":"2018","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A dataset for diverse, explainable multi-hop question answering. In Proceedings of EMNLP. 2369-2380. https:\/\/aclanthology.org\/D18-1259","journal-title":"Proceedings of EMNLP."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591813"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.95"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.414"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.mrl-1.12"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00595"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.388"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637870"},{"key":"e_1_3_2_1_59_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. ArXiv preprint abs\/2303.18223 (2023). https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"e_1_3_2_1_60_1","volume-title":"Large language models for information retrieval: A survey. ArXiv preprint abs\/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 abs\/2308.07107 (2023). https:\/\/arxiv.org\/abs\/2308.07107"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.250"}],"event":{"name":"SIGIR-AP 2025:Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","location":"Xi'an China","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:16:28Z","timestamp":1764782188000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767695.3769491"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":61,"alternative-id":["10.1145\/3767695.3769491","10.1145\/3767695"],"URL":"https:\/\/doi.org\/10.1145\/3767695.3769491","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}