{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:39:16Z","timestamp":1776443956376,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730112","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:41:01Z","timestamp":1752457261000},"page":"1262-1271","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5760-9285","authenticated-orcid":false,"given":"Yuhao","family":"Wang","sequence":"first","affiliation":[{"name":"GSAI, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0562-9911","authenticated-orcid":false,"given":"Ruiyang","family":"Ren","sequence":"additional","affiliation":[{"name":"GSAI, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2968-6126","authenticated-orcid":false,"given":"Yucheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8333-6196","authenticated-orcid":false,"given":"Wayne Xin","family":"Zhao","sequence":"additional","affiliation":[{"name":"GSAI, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1727-6321","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8254-1561","authenticated-orcid":false,"given":"Hua","family":"Wu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0672-7468","authenticated-orcid":false,"given":"Haifeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? arXiv preprint arXiv:2010.05607","author":"Bastings Jasmijn","year":"2020","unstructured":"Jasmijn Bastings and Katja Filippova. 2020. The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? arXiv preprint arXiv:2010.05607 (2020)."},{"key":"e_1_3_2_1_2_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"e_1_3_2_1_4_1","volume-title":"Wayne Xin Zhao, and Ji-Rong Wen","author":"Cheng Xiaoxue","year":"2025","unstructured":"Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, and Ji-Rong Wen. 2025. Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking. arXiv preprint arXiv:2501.01306 (2025)."},{"key":"e_1_3_2_1_5_1","volume-title":"Hongzhi Zhang, Fuzheng Zhang, Di Zhang, Kun Gai, and Ji-Rong Wen.","author":"Cheng Xiaoxue","year":"2024","unstructured":"Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, Hongzhi Zhang, Fuzheng Zhang, Di Zhang, Kun Gai, and Ji-Rong Wen. 2024. Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector. arXiv preprint arXiv:2406.11277 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Bingning Wang, and Weipeng Chen.","author":"Dong Zican","year":"2025","unstructured":"Zican Dong, Junyi Li, Jinhao Jiang, Mingyu Xu, Wayne Xin Zhao, Bingning Wang, and Weipeng Chen. 2025. LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation. arXiv preprint arXiv:2502.07365 (2025)."},{"key":"e_1_3_2_1_7_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_8_1","volume-title":"A Mathematical Framework for Transformer Circuits. Transformer Circuits Thread","author":"Elhage Nelson","year":"2021","unstructured":"Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Nicholas Joseph, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Nova DasSarma, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amodei, Tom Brown, Jack Clark, Jared Kaplan, Sam McCandlish, and Chris Olah. 2021. A Mathematical Framework for Transformer Circuits. Transformer Circuits Thread (2021). https:\/\/transformer-circuits.pub\/2021\/framework\/index.html."},{"key":"e_1_3_2_1_9_1","volume-title":"Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Hanna Michael","year":"2024","unstructured":"Michael Hanna, Ollie Liu, and Alexandre Variengien. 2024. How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness? arXiv preprint arXiv:2004.03685","author":"Jacovi Alon","year":"2020","unstructured":"Alon Jacovi and Yoav Goldberg. 2020. Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness? arXiv preprint arXiv:2004.03685 (2020)."},{"key":"e_1_3_2_1_12_1","volume-title":"Tug-of-war between knowledge: Exploring and resolving knowledge conflicts in retrieval-augmented language models. arXiv preprint arXiv:2402.14409","author":"Jin Zhuoran","year":"2024","unstructured":"Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Qiuxia Li, and Jun Zhao. 2024a. Tug-of-war between knowledge: Exploring and resolving knowledge conflicts in retrieval-augmented language models. arXiv preprint arXiv:2402.14409 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"Cutting off the head ends the conflict: A mechanism for interpreting and mitigating knowledge conflicts in language models. arXiv preprint arXiv:2402.18154","author":"Jin Zhuoran","year":"2024","unstructured":"Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, and Jun Zhao. 2024b. Cutting off the head ends the conflict: A mechanism for interpreting and mitigating knowledge conflicts in language models. arXiv preprint arXiv:2402.18154 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_16_1","unstructured":"Tom Kwiatkowski Jennimaria Palomaki Michael Collins Ankur Parikh Chris Alberti Danielle Epstein Illia Polosukhin Matthew Kelcey Jacob Devlin Kenton Lee et al. [n.d.]. Natural Questions: a Benchmark for Question Answering Research. ( [n. d.])."},{"key":"e_1_3_2_1_17_1","volume-title":"Paperqa: Retrieval-augmented generative agent for scientific research. arXiv preprint arXiv:2312.07559","author":"L\u00e1la Jakub","year":"2023","unstructured":"Jakub L\u00e1la, Odhran O'Donoghue, Aleksandar Shtedritski, Sam Cox, Samuel G Rodriques, and Andrew D White. 2023. Paperqa: Retrieval-augmented generative agent for scientific research. arXiv preprint arXiv:2312.07559 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1612"},{"key":"e_1_3_2_1_19_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, et al., 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, Vol. 33 (2020), 9459-9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","volume-title":"Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models. arXiv preprint arXiv:2403.19521","author":"Lv Ang","year":"2024","unstructured":"Ang Lv, Kaiyi Zhang, Yuhan Chen, Yulong Wang, Lifeng Liu, Ji-Rong Wen, Jian Xie, and Rui Yan. 2024. Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models. arXiv preprint arXiv:2403.19521 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"e_1_3_2_1_22_1","volume-title":"Are sixteen heads really better than one? Advances in neural information processing systems","author":"Michel Paul","year":"2019","unstructured":"Paul Michel, Omer Levy, and Graham Neubig. 2019. Are sixteen heads really better than one? Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_2_1_24_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_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_1_26_1","volume-title":"QiaoQiao She, Hua Wu, Haifeng Wang, and Ji-Rong Wen.","author":"Ren Ruiyang","year":"2021","unstructured":"Ruiyang Ren, Shangwen Lv, Yingqi Qu, Jing Liu, Wayne Xin Zhao, QiaoQiao She, Hua Wu, Haifeng Wang, and Ji-Rong Wen. 2021a. PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2173-2183."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"e_1_3_2_1_28_1","volume-title":"Wenjie Wang, and Tat-Seng Chua.","author":"Ren Ruiyang","year":"2025","unstructured":"Ruiyang Ren, Yuhao Wang, Junyi Li, Jinhao Jiang, Wayne Xin Zhao, Wenjie Wang, and Tat-Seng Chua. 2025. Holistically Guided Monte Carlo Tree Search for Intricate Information Seeking. arXiv preprint arXiv:2502.04751 (2025)."},{"key":"e_1_3_2_1_29_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_30_1","volume-title":"Glu variants improve transformer. arXiv preprint arXiv:2002.05202","author":"Shazeer Noam","year":"2020","unstructured":"Noam Shazeer. 2020. Glu variants improve transformer. arXiv preprint arXiv:2002.05202 (2020)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.309"},{"key":"e_1_3_2_1_32_1","volume-title":"Binbin Hu, Ziqi Liu, and Zhiqiang Zhang.","author":"Tang Xinyu","year":"2025","unstructured":"Xinyu Tang, Xiaolei Wang, Zhihao Lv, Yingqian Min, Wayne Xin Zhao, Binbin Hu, Ziqi Liu, and Zhiqiang Zhang. 2025. Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering. arXiv preprint arXiv:2503.11314 (2025)."},{"key":"e_1_3_2_1_33_1","volume-title":"Siyuan Lu, Yaliang Li, and Ji-Rong Wen.","author":"Tang Xinyu","year":"2024","unstructured":"Xinyu Tang, Xiaolei Wang, Wayne Xin Zhao, Siyuan Lu, Yaliang Li, and Ji-Rong Wen. 2024c. Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers. arXiv preprint arXiv:2402.17564 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"Wayne Xin Zhao, and Ji-Rong Wen","author":"Tang Xinyu","year":"2024","unstructured":"Xinyu Tang, Xiaolei Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2024b. Dawn-icl: Strategic planning of problem-solving trajectories for zero-shot in-context learning. arXiv preprint arXiv:2410.20215 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_36_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. [n.d.]. Attention Is All You Need. ( [n. d.])."},{"key":"e_1_3_2_1_37_1","volume-title":"Label words are anchors: An information flow perspective for understanding in-context learning. arXiv preprint arXiv:2305.14160","author":"Wang Lean","year":"2023","unstructured":"Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, and Xu Sun. 2023. Label words are anchors: An information flow perspective for understanding in-context learning. arXiv preprint arXiv:2305.14160 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Jing Liu, and Ji-Rong Wen.","author":"Wang Yuhao","year":"2024","unstructured":"Yuhao Wang, Ruiyang Ren, Junyi Li, Wayne Xin Zhao, Jing Liu, and Ji-Rong Wen. 2024. REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering. arXiv preprint arXiv:2402.17497 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Attentional factorization machines: Learning the weight of feature interactions via attention networks. arXiv preprint arXiv:1708.04617","author":"Xiao Jun","year":"2017","unstructured":"Jun Xiao, Hao Ye, Xiangnan He, Hanwang Zhang, Fei Wu, and Tat-Seng Chua. 2017. Attentional factorization machines: Learning the weight of feature interactions via attention networks. arXiv preprint arXiv:1708.04617 (2017)."},{"key":"e_1_3_2_1_40_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2369-2380","author":"Yang Zhilin","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 the 2018 Conference on Empirical Methods in Natural Language Processing. 2369-2380."},{"key":"e_1_3_2_1_42_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 arXiv:2303.18223 (2023). gr"}],"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\/3726302.3730112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:21:22Z","timestamp":1755868882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":42,"alternative-id":["10.1145\/3726302.3730112","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730112","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"}}]}}