{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:20Z","timestamp":1784179100016,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Quan Cheng Laboratory Funding","award":["No.QCLZD202301"],"award-info":[{"award-number":["No.QCLZD202301"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,28]]},"DOI":"10.1145\/3696410.3714608","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T22:52:18Z","timestamp":1745362338000},"page":"4386-4395","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Decoupling Knowledge and Context: An Efficient and Effective Retrieval Augmented Generation Framework via Cross Attention"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6858-5303","authenticated-orcid":false,"given":"Qian","family":"Dong","sequence":"first","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5030-709X","authenticated-orcid":false,"given":"Qingyao","family":"Ai","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6524-9195","authenticated-orcid":false,"given":"Hongning","family":"Wang","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6857-261X","authenticated-orcid":false,"given":"Yiding","family":"Liu","sequence":"additional","affiliation":[{"name":"TikTok, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8766-8610","authenticated-orcid":false,"given":"Haitao","family":"Li","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8718-9402","authenticated-orcid":false,"given":"Weihang","family":"Su","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-4512","authenticated-orcid":false,"given":"Yiqun","family":"Liu","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8762-8268","authenticated-orcid":false,"given":"Shaoping","family":"Ma","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AI@Meta. 2024. Llama 3 Model Card. (2024). https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"e_1_3_2_1_2_1","volume-title":"Gqa: Training generalized multi-query transformer models from multi-head checkpoints. arXiv preprint arXiv:2305.13245","author":"Ainslie Joshua","year":"2023","unstructured":"Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebr\u00f3n, and Sumit Sanghai. 2023. Gqa: Training generalized multi-query transformer models from multi-head checkpoints. arXiv preprint arXiv:2305.13245 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Language models are few-shot learners. arXiv preprint arXiv:2005.14165","author":"Brown Tom B","year":"2020","unstructured":"Tom B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)."},{"key":"e_1_3_2_1_4_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, Vol. 24, 240 (2023), 1--113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_5_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_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"Wizard of wikipedia: Knowledge-powered conversational agents. arXiv preprint arXiv:1811.01241","author":"Dinan Emily","year":"2018","unstructured":"Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. 2018. Wizard of wikipedia: Knowledge-powered conversational agents. arXiv preprint arXiv:1811.01241 (2018)."},{"key":"e_1_3_2_1_8_1","volume-title":"Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval. arXiv preprint arXiv:2306.02371","author":"Dong Qian","year":"2023","unstructured":"Qian Dong, Yiding Liu, Qingyao Ai, Haitao Li, Shuaiqiang Wang, Yiqun Liu, Dawei Yin, and Shaoping Ma. 2023. I^ 3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval. arXiv preprint arXiv:2306.02371 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657689"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531997"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73197-7_6"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Elsahar Hady","year":"2018","unstructured":"Hady Elsahar, Pavlos Vougiouklis, Arslen Remaci, Christophe Gravier, Jonathon Hare, Frederique Laforest, and Elena Simperl. 2018. T-rex: A large scale alignment of natural language with knowledge base triples. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657743"},{"key":"e_1_3_2_1_14_1","volume-title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models. arXiv preprint arXiv:2405.14831","author":"Guti\u00e9rrez Bernal Jim\u00e9nez","year":"2024","unstructured":"Bernal Jim\u00e9nez Guti\u00e9rrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models. arXiv preprint arXiv:2405.14831 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR, 3929--3938","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 International conference on machine learning. PMLR, 3929--3938."},{"key":"e_1_3_2_1_16_1","volume-title":"Saku Sugawara, and Akiko Aizawa.","author":"Ho Xanh","year":"2020","unstructured":"Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps. arXiv preprint arXiv:2011.01060 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG. arXiv preprint arXiv:2410","author":"Jin Bowen","year":"2024","unstructured":"Bowen Jin, Jinsung Yoon, Jiawei Han, and Sercan O Arik. 2024. Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG. arXiv preprint arXiv:2410.05983 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906","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. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_1_20_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_21_1","unstructured":"Quinn Leng Jacob Portes Sam Havens Matei Zaharia and Michael Carbin. 2024. Long Context RAG Performance of LLMs. https:\/\/www.databricks.com\/blog\/long-context-rag-performance-llms Published in Mosaic AI Research. Accessed: 2024--10--13."},{"key":"e_1_3_2_1_22_1","volume-title":"Zero-shot relation extraction via reading comprehension. arXiv preprint arXiv:1706.04115","author":"Levy Omer","year":"2017","unstructured":"Omer Levy, Minjoon Seo, Eunsol Choi, and Luke Zettlemoyer. 2017. Zero-shot relation extraction via reading comprehension. arXiv preprint arXiv:1706.04115 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461","author":"Lewis M","year":"2019","unstructured":"M Lewis. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)."},{"key":"e_1_3_2_1_24_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. 2020a. 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_25_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. 2020b. 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_26_1","volume-title":"DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment. arXiv preprint arXiv:2403.18435","author":"Li Haitao","year":"2024","unstructured":"Haitao Li, Qingyao Ai, Xinyan Han, Jia Chen, Qian Dong, Yiqun Liu, Chong Chen, and Qi Tian. 2024a. DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment. arXiv preprint arXiv:2403.18435 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods. arXiv preprint arXiv:2412.05579","author":"Li Haitao","year":"2024","unstructured":"Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, and Yiqun Liu. 2024b. LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods. arXiv preprint arXiv:2412.05579 (2024)."},{"key":"e_1_3_2_1_28_1","unstructured":"Shilong Li Yancheng He Hangyu Guo Xingyuan Bu Ge Bai Jie Liu Jiaheng Liu Xingwei Qu Yangguang Li Wanli Ouyang et al. 2024c. GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models. arXiv preprint arXiv:2406.14550 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_1_30_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_32_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. arXiv preprint arXiv:2110.07367 (2021)."},{"key":"e_1_3_2_1_33_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_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_2_1_35_1","volume-title":"Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval. arXiv preprint arXiv:2312.10661","author":"Su Weihang","year":"2023","unstructured":"Weihang Su, Qingyao Ai, Xiangsheng Li, Jia Chen, Yiqun Liu, Xiaolong Wu, and Shengluan Hou. 2023. Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval. arXiv preprint arXiv:2312.10661 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","unstructured":"Weihang Su Yichen Tang Qingyao Ai Zhijing Wu and Yiqun Liu. 2024b. DRAGIN: Dynamic Retrieval Augmented Generation based on the Real-time Information Needs of Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Lun-Wei Ku Andre Martins and Vivek Srikumar (Eds.). Association for Computational Linguistics Bangkok Thailand 12991--13013. https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.702","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_37_1","volume-title":"The web as a knowledge-base for answering complex questions. arXiv preprint arXiv:1803.06643","author":"Talmor Alon","year":"2018","unstructured":"Alon Talmor and Jonathan Berant. 2018. The web as a knowledge-base for answering complex questions. arXiv preprint arXiv:1803.06643 (2018)."},{"key":"e_1_3_2_1_38_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_40_1","volume-title":"How faithful are RAG models? Quantifying the tug-of-war between RAG and LLMs' internal prior. arXiv e-prints","author":"Wu Kevin","year":"2024","unstructured":"Kevin Wu, Eric Wu, and James Zou. 2024. How faithful are RAG models? Quantifying the tug-of-war between RAG and LLMs' internal prior. arXiv e-prints (2024), arXiv--2404."},{"key":"e_1_3_2_1_41_1","volume-title":"RetroMAE: Pre-training retrieval-oriented language models via masked auto-encoder. arXiv preprint arXiv:2205.12035","author":"Xiao Shitao","year":"2022","unstructured":"Shitao Xiao, Zheng Liu, Yingxia Shao, and Zhao Cao. 2022. RetroMAE: Pre-training retrieval-oriented language models via masked auto-encoder. arXiv preprint arXiv:2205.12035 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Inference scaling for long-context retrieval augmented generation. arXiv preprint arXiv:2410.04343","author":"Yue Zhenrui","year":"2024","unstructured":"Zhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui, Rolf Jagerman, Hansi Zeng, Zhen Qin, Dong Wang, Xuanhui Wang, and Michael Bendersky. 2024. Inference scaling for long-context retrieval augmented generation. arXiv preprint arXiv:2410.04343 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric Agents. arXiv preprint arXiv:2407.09394","author":"Zerhoudi Saber","year":"2024","unstructured":"Saber Zerhoudi and Michael Granitzer. 2024. PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric Agents. arXiv preprint arXiv:2407.09394 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Knowgpt: Black-box knowledge injection for large language models. arXiv preprint arXiv:2312.06185","author":"Zhang Qinggang","year":"2023","unstructured":"Qinggang Zhang, Junnan Dong, Hao Chen, Xiao Huang, Daochen Zha, and Zailiang Yu. 2023. Knowgpt: Black-box knowledge injection for large language models. arXiv preprint arXiv:2312.06185 (2023)."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714608","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:34Z","timestamp":1750295914000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714608"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":44,"alternative-id":["10.1145\/3696410.3714608","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714608","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}