{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:16:18Z","timestamp":1755839778500,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3680052","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"4718-4725","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Boosting LLM-based Relevance Modeling with Distribution-Aware Robust Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2361-5721","authenticated-orcid":false,"given":"Hong","family":"Liu","sequence":"first","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9938-7779","authenticated-orcid":false,"given":"Saisai","family":"Gong","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9309-3323","authenticated-orcid":false,"given":"Yixin","family":"Ji","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6450-8960","authenticated-orcid":false,"given":"Kaixin","family":"Wu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1163-513X","authenticated-orcid":false,"given":"Jia","family":"Xu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7596-4945","authenticated-orcid":false,"given":"Jinjie","family":"Gu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The Linguistic Structure of English Web-Search Queries. In 2008 Conference on Empirical Methods in Natural Language Processing. 1021--1030","author":"Barr Cory","year":"2008","unstructured":"Cory Barr, Rosie Jones, and Moira Regelson. 2008. The Linguistic Structure of English Web-Search Queries. In 2008 Conference on Empirical Methods in Natural Language Processing. 1021--1030."},{"key":"e_1_3_2_1_2_1","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33. 1877--1901."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615457"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Yiming Cui Wanxiang Che Ting Liu Bing Qin and Ziqing Yang. 2021. Pre-Training with Whole Word Masking for Chinese BERT. https:\/\/doi.org\/10.1109\/TASLP.2021.3124365","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596490"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"volume-title":"Proceedings of the 2023 ACM SIGIR International Conference on Theory of Information Retrieval. 39--50","author":"Faggioli Guglielmo","key":"e_1_3_2_1_8_1","unstructured":"Guglielmo Faggioli, Laura Dietz, Charles L. A. Clarke, Gianluca Demartini, Matthias Hagen, and et al. 2023. Perspectives on Large Language Models for Relevance Judgment. In Proceedings of the 2023 ACM SIGIR International Conference on Theory of Information Retrieval. 39--50."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450009"},{"volume-title":"Proceedings of the 25th ACM International Conference on Information and Knowledge Management. 55--64","author":"Guo Jiafeng","key":"e_1_3_2_1_10_1","unstructured":"Jiafeng Guo, Yixing Fan, Qingyao Ai, and W. Bruce Croft. 2016. A Deep Relevance Matching Model for Ad-hoc Retrieval. In Proceedings of the 25th ACM International Conference on Information and Knowledge Management. 55--64."},{"volume-title":"Proceedings of the 25th ACM International Conference on Information and Knowledge Management. 701--710","author":"Guo Jiafeng","key":"e_1_3_2_1_11_1","unstructured":"Jiafeng Guo, Yixing Fan, Qingyao Ai, and W. Bruce Croft. 2016. Semantic Matching by Non-Linear Word Transportation for Information Retrieval. In Proceedings of the 25th ACM International Conference on Information and Knowledge Management. 701--710."},{"key":"e_1_3_2_1_12_1","volume-title":"The Tenth International Conference on Learning Representations.","author":"He Junxian","year":"2022","unstructured":"Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, and Graham Neubig. 2022. Towards a Unified View of Parameter-Efficient Transfer Learning. In The Tenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_1_14_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations.","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 The Tenth International Conference on Learning Representations."},{"volume-title":"Proceedings of the 22nd ACM International Conference on Information and Knowledge Management. 2333--2338","author":"Huang Po-Sen","key":"e_1_3_2_1_15_1","unstructured":"Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry P. Heck. 2013. Learning deep structured semantic models for web search using clickthrough data. In Proceedings of the 22nd ACM International Conference on Information and Knowledge Management. 2333--2338."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911531"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_18_1","volume-title":"The Tenth International Conference on Learning Representations.","author":"Kumar Ananya","year":"2022","unstructured":"Ananya Kumar, Aditi Raghunathan, Robbie Matthew Jones, Tengyu Ma, and Percy Liang. 2022. Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution. In The Tenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","unstructured":"Kimin Lee Kibok Lee Honglak Lee and Jinwoo Shin. 2018. A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks. In Advances in Neural Information Processing Systems 31. 7167--7177."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_3_2_1_21_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. arxiv","author":"Liu Yinhan","year":"1907","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arxiv: 1907.11692"},{"key":"e_1_3_2_1_22_1","volume-title":"Learning with Mixture of Prototypes for Out-of-Distribution Detection. In The Twelfth International Conference on Learning Representations.","author":"Lu Haodong","year":"2024","unstructured":"Haodong Lu, Dong Gong, Shuo Wang, Jason Xue, Lina Yao, and Kristen Moore. 2024. Learning with Mixture of Prototypes for Out-of-Distribution Detection. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412747"},{"key":"e_1_3_2_1_24_1","unstructured":"Xueguang Ma Liang Wang Nan Yang Furu Wei and Jimmy Lin. 2023. Fine-Tuning LLaMA for Multi-Stage Text Retrieval. arxiv: 2310.08319"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592032"},{"key":"e_1_3_2_1_26_1","volume-title":"Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Nick Barnes, and Ajmal Mian.","author":"Naveed Humza","year":"2023","unstructured":"Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Nick Barnes, and Ajmal Mian. 2023. A Comprehensive Overview of Large Language Models. arxiv: 2307.06435"},{"key":"e_1_3_2_1_27_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad and et al. 2023. GPT-4 Technical Report. arxiv: 2303.08774"},{"key":"e_1_3_2_1_28_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll L. Wainwright and et al. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems 35. 27730--27744."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10341"},{"key":"e_1_3_2_1_30_1","unstructured":"Bo Peng Xinyi Ling Ziru Chen Huan Sun and Xia Ning. 2024. eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale High-quality Instruction Data. arxiv: 2402.08831"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2577348"},{"key":"e_1_3_2_1_36_1","volume-title":"Out-of-Distribution Detection with Deep Nearest Neighbors. In International Conference on Machine Learning. PMLR","author":"Sun Yiyou","year":"2022","unstructured":"Yiyou Sun, Yifei Ming, Xiaojin Zhu, and Yixuan Li. 2022. Out-of-Distribution Detection with Deep Nearest Neighbors. In International Conference on Machine Learning. PMLR, 20827--20840."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657707"},{"key":"e_1_3_2_1_38_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aur\u00e9lien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arxiv: 2302.13971"},{"key":"e_1_3_2_1_39_1","volume-title":"Two-stage LLM Fine-tuning with Less Specialization and More Generalization. In The Twelfth International Conference on Learning Representations.","author":"Wang Yihan","year":"2024","unstructured":"Yihan Wang, Si Si, Daliang Li, Michal Lukasik, Felix Yu, Cho-Jui Hsieh, Inderjit Dhillon, and Sanjiv Kumar. 2024. Two-stage LLM Fine-tuning with Less Specialization and More Generalization. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_40_1","volume-title":"An Empirical Evaluation of Confidence Elicitation in LLMs. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=gjeQKFxFpZ","author":"Xiong Miao","year":"2024","unstructured":"Miao Xiong, Zhiyuan Hu, Xinyang Lu, YIFEI LI, Jie Fu, Junxian He, and Bryan Hooi. 2024. Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=gjeQKFxFpZ"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000076"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Haoran Yang Yumeng Zhang Jiaqi Xu Hongyuan Lu Pheng-Ann Heng and Wai Lam. 2024. Unveiling the Generalization Power of Fine-Tuned Large Language Models. arxiv: 2403.09162","DOI":"10.18653\/v1\/2024.naacl-long.51"},{"key":"e_1_3_2_1_43_1","unstructured":"Jingkang Yang Kaiyang Zhou Yixuan Li and Ziwei Liu. 2021. Generalized Out-of-Distribution Detection: A Survey. arxiv: 2110.11334"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.276"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Linyi Yang Shuibai Zhang Libo Qin Yafu Li Yidong Wang Hanmeng Liu Jindong Wang Xing Xie and Yue Zhang. 2023. GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective. In Findings of the Association for Computational Linguistics. 12731--12750.","DOI":"10.18653\/v1\/2023.findings-acl.806"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.514"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615500"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Boise ID USA","acronym":"CIKM '24"},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680052","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3680052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:17Z","timestamp":1750294697000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":47,"alternative-id":["10.1145\/3627673.3680052","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3680052","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}