{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:10:05Z","timestamp":1755889805068,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"name":"Youth Innova-tion Promotion Association CAS","award":["2023111"],"award-info":[{"award-number":["2023111"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472426, 62276248"],"award-info":[{"award-number":["62472426, 62276248"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFA1008704"],"award-info":[{"award-number":["2023YFA1008704"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Funds of Renmin University of China","award":["RUC24QSDL013"],"award-info":[{"award-number":["RUC24QSDL013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730038","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:18:36Z","timestamp":1752455916000},"page":"370-380","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Mitigating Source Bias with LLM Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7549-0860","authenticated-orcid":false,"given":"Sunhao","family":"Dai","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2453-9138","authenticated-orcid":false,"given":"Yuqi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1161-8546","authenticated-orcid":false,"given":"Liang","family":"Pang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6297-616X","authenticated-orcid":false,"given":"Zhuoyang","family":"Li","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1811-129X","authenticated-orcid":false,"given":"Zhaocheng","family":"Du","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8795-8953","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7170-111X","authenticated-orcid":false,"given":"Jun","family":"Xu","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt. arXiv preprint arXiv:2303.04226","author":"Cao Yihan","year":"2023","unstructured":"Yihan Cao, Siyu Li, Yixin Liu, Zhiling Yan, Yutong Dai, Philip S Yu, and Lichao Sun. 2023. A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt. arXiv preprint arXiv:2303.04226 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.798"},{"key":"e_1_3_2_1_3_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_4_1","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung Hyung Won","year":"2024","unstructured":"Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al., 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research, Vol. 25, 70 (2024), 1-53.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_5_1","volume-title":"Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration. Findings of the Association for Computational Linguistics: ACL 2024","author":"Dai Sunhao","year":"2024","unstructured":"Sunhao Dai, Weihao Liu, Yuqi Zhou, Liang Pang, Rongju Ruan, Gang Wang, Zhenhua Dong, Jun Xu, and Ji-Rong Wen. 2024a. Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration. Findings of the Association for Computational Linguistics: ACL 2024 (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671458"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701551.3703478"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671882"},{"key":"e_1_3_2_1_9_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos. arXiv preprint arXiv:2502.07327","author":"Gao Haowen","year":"2025","unstructured":"Haowen Gao, Liang Pang, Shicheng Xu, Leigang Qu, Tat-Seng Chua, Huawei Shen, and Xueqi Cheng. 2025. Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos. arXiv preprint arXiv:2502.07327 (2025)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"e_1_3_2_1_12_1","volume-title":"Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)."},{"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 International Conference on Learning Representations.","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"Unsupervised Dense Information Retrieval with Contrastive Learning. Transactions on Machine Learning Research","author":"Izacard Gautier","year":"2022","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. Unsupervised Dense Information Retrieval with Contrastive Learning. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_2_1_16_1","unstructured":"Jiaming Ji Tianyi Qiu Boyuan Chen Borong Zhang Hantao Lou Kaile Wang Yawen Duan Zhonghao He Jiayi Zhou Zhaowei Zhang et al. 2023. Ai alignment: A comprehensive survey. arXiv preprint arXiv:2310.19852 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Alignment of language agents. arXiv preprint arXiv:2103.14659","author":"Kenton Zachary","year":"2021","unstructured":"Zachary Kenton, Tom Everitt, Laura Weidinger, Iason Gabriel, Vladimir Mikulik, and Geoffrey Irving. 2021. Alignment of language agents. arXiv preprint arXiv:2103.14659 (2021)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_20_1","volume-title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. arXiv preprint arXiv:2302.07452","author":"Lin Sheng-Chieh","year":"2023","unstructured":"Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, and Xilun Chen. 2023. How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. arXiv preprint arXiv:2302.07452 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. choice","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, Vol. 2640 (2016), 660."},{"key":"e_1_3_2_1_22_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems Vol. 35 (2022) 27730-27744."},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Rafailov Rafael","year":"2024","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2024. Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07566-y"},{"key":"e_1_3_2_1_26_1","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon Nisan","year":"2020","unstructured":"Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learning to summarize with human feedback. Advances in Neural Information Processing Systems, Vol. 33 (2020), 3008-3021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics","author":"Tan Hexiang","year":"2024","unstructured":"Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, and Xueqi Cheng. 2024. Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts for Open-Domain QA? Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","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 Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3451964.3451965","article-title":"TREC-COVID: constructing a pandemic information retrieval test collection","volume":"54","author":"Voorhees Ellen","year":"2021","unstructured":"Ellen Voorhees, Tasmeer Alam, Steven Bedrick, Dina Demner-Fushman, William R Hersh, Kyle Lo, Kirk Roberts, Ian Soboroff, and Lucy Lu Wang. 2021. TREC-COVID: constructing a pandemic information retrieval test collection. In ACM SIGIR Forum, Vol. 54. 1-12.","journal-title":"ACM SIGIR Forum"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.609"},{"key":"e_1_3_2_1_31_1","volume-title":"Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents. In 13th International Conference on Learning Representations, ICLR","author":"Wang Haoyu","year":"2025","unstructured":"Haoyu Wang, Sunhao Dai, Haiyuan Zhao, Liang Pang, Xiao Zhang, Gang Wang, Zhenhua Dong, Jun Xu, and Ji-Rong Wen. 2025. Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents. In 13th International Conference on Learning Representations, ICLR 2025."},{"key":"e_1_3_2_1_32_1","volume-title":"A Survey on Data Selection for LLM Instruction Tuning. arXiv preprint arXiv:2402.05123","author":"Wang Jiahao","year":"2024","unstructured":"Jiahao Wang, Bolin Zhang, Qianlong Du, Jiajun Zhang, and Dianhui Chu. 2024. A Survey on Data Selection for LLM Instruction Tuning. arXiv preprint arXiv:2402.05123 (2024)."},{"key":"e_1_3_2_1_33_1","volume-title":"Aligning large language models with human: A survey. arXiv preprint arXiv:2307.12966","author":"Wang Yufei","year":"2023","unstructured":"Yufei Wang, Wanjun Zhong, Liangyou Li, Fei Mi, Xingshan Zeng, Wenyong Huang, Lifeng Shang, Xin Jiang, and Qun Liu. 2023. Aligning large language models with human: A survey. arXiv preprint arXiv:2307.12966 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le.","author":"Wei Jason","year":"2021","unstructured":"Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)."},{"key":"e_1_3_2_1_35_1","volume-title":"Ai-generated content (aigc): A survey. arXiv preprint arXiv:2304.06632","author":"Wu Jiayang","year":"2023","unstructured":"Jiayang Wu, Wensheng Gan, Zefeng Chen, Shicheng Wan, and Hong Lin. 2023. Ai-generated content (aigc): A survey. arXiv preprint arXiv:2304.06632 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"e_1_3_2_1_37_1","volume-title":"C-pack: Packaged resources to advance general chinese embedding. arXiv preprint arXiv:2309.07597","author":"Xiao Shitao","year":"2023","unstructured":"Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff, Defu Lian, and Jian-Yun Nie. 2023. C-pack: Packaged resources to advance general chinese embedding. arXiv preprint arXiv:2309.07597 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657750"},{"key":"e_1_3_2_1_40_1","volume-title":"Rrhf: Rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302","author":"Yuan Zheng","year":"2023","unstructured":"Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, and Fei Huang. 2023. Rrhf: Rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302 (2023)."},{"key":"e_1_3_2_1_41_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. 2023b. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Slic-hf: Sequence likelihood calibration with human feedback. arXiv preprint arXiv:2305.10425","author":"Zhao Yao","year":"2023","unstructured":"Yao Zhao, Rishabh Joshi, Tianqi Liu, Misha Khalman, Mohammad Saleh, and Peter J Liu. 2023a. Slic-hf: Sequence likelihood calibration with human feedback. arXiv preprint arXiv:2305.10425 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729972"},{"key":"e_1_3_2_1_45_1","volume-title":"Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593","author":"Ziegler Daniel M","year":"2019","unstructured":"Daniel M Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2019. Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593 (2019)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"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\/3726302.3730038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:29:53Z","timestamp":1755887393000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":45,"alternative-id":["10.1145\/3726302.3730038","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730038","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"}}]}}