{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:02:50Z","timestamp":1775815370984,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"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":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709240","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:44:43Z","timestamp":1743792283000},"page":"1150-1160","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Tackling the Length Barrier: Dynamic Context Browsing for Knowledge-Intensive Task"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4011-5673","authenticated-orcid":false,"given":"Hongjin","family":"Qian","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China and Beijing Academy of Artificial Intelligence, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-8466","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1926-7433","authenticated-orcid":false,"given":"Peitian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5648-568X","authenticated-orcid":false,"given":"Kelong","family":"Mao","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3530-3787","authenticated-orcid":false,"given":"Yujia","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0144-1775","authenticated-orcid":false,"given":"Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9781-948X","authenticated-orcid":false,"given":"Zhicheng","family":"Dou","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Marah Abdin Sam Ade Jacobs Ammar Ahmad Awan Jyoti Aneja Ahmed Awadallah Hany Awadalla Nguyen Bach Amit Bahree Arash Bakhtiari Harkirat Behl Alon Benhaim Misha Bilenko Johan Bjorck S\u00e9bastien Bubeck Martin Cai Caio C\u00e9sar Teodoro Mendes Weizhu Chen Vishrav Chaudhary Parul Chopra Allie Del Giorno Gustavo de Rosa Matthew Dixon Ronen Eldan Dan Iter Amit Garg Abhishek Goswami Suriya Gunasekar Emman Haider Junheng Hao Russell J. Hewett Jamie Huynh Mojan Javaheripi Xin Jin Piero Kauffmann Nikos Karampatziakis Dongwoo Kim Mahoud Khademi Lev Kurilenko James R. Lee Yin Tat Lee Yuanzhi Li Chen Liang Weishung Liu Eric Lin Zeqi Lin Piyush Madan Arindam Mitra Hardik Modi Anh Nguyen Brandon Norick Barun Patra Daniel Perez-Becker Thomas Portet Reid Pryzant Heyang Qin Marko Radmilac Corby Rosset Sambudha Roy Olatunji Ruwase Olli Saarikivi Amin Saied Adil Salim Michael Santacroce Shital Shah Ning Shang Hiteshi Sharma Xia Song Masahiro Tanaka Xin Wang Rachel Ward Guanhua Wang Philipp Witte Michael Wyatt Can Xu Jiahang Xu Sonali Yadav Fan Yang Ziyi Yang Donghan Yu Chengruidong Zhang Cyril Zhang Jianwen Zhang Li Lyna Zhang Yi Zhang Yue Zhang Yunan Zhang and Xiren Zhou. 2024. Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone. arxiv: 2404.14219 [cs.CL]"},{"key":"e_1_3_2_2_2_1","volume-title":"Social cognition and the human brain. Trends in cognitive sciences","author":"Adolphs Ralph","year":"1999","unstructured":"Ralph Adolphs. 1999. Social cognition and the human brain. Trends in cognitive sciences, Vol. 3, 12 (1999), 469--479."},{"key":"e_1_3_2_2_3_1","volume-title":"Yi: Open Foundation Models by 01.AI. arxiv: 2403.04652 [cs.CL]","author":"Young Alex","year":"2024","unstructured":"01. AI,:, Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Heng Li, Jiangcheng Zhu, Jianqun Chen, Jing Chang, Kaidong Yu, Peng Liu, Qiang Liu, Shawn Yue, Senbin Yang, Shiming Yang, Tao Yu, Wen Xie, Wenhao Huang, Xiaohui Hu, Xiaoyi Ren, Xinyao Niu, Pengcheng Nie, Yuchi Xu, Yudong Liu, Yue Wang, Yuxuan Cai, Zhenyu Gu, Zhiyuan Liu, and Zonghong Dai. 2024. Yi: Open Foundation Models by 01.AI. arxiv: 2403.04652 [cs.CL]"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/364447.364549"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Jianlv Chen Shitao Xiao Peitian Zhang Kun Luo Defu Lian and Zheng Liu. 2023. BGE M3-Embedding: Multi-Lingual Multi-Functionality Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. arxiv: 2309.07597 [cs.CL]","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"e_1_3_2_2_7_1","volume-title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Chen Yukang","year":"2024","unstructured":"Yukang Chen, Shengju Qian, Haotian Tang, Xin Lai, Zhijian Liu, Song Han, and Jiaya Jia. 2024. LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7--11, 2024. OpenReview.net."},{"key":"e_1_3_2_2_8_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03--30-vicuna\/"},{"key":"e_1_3_2_2_9_1","volume-title":"Elements of information theory","author":"Cover Thomas M","unstructured":"Thomas M Cover. 1999. Elements of information theory. John Wiley & Sons."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.365"},{"key":"e_1_3_2_2_11_1","unstructured":"DeepSeek-AI. 2024. DeepSeek-V2: A Strong Economical and Efficient Mixture-of-Experts Language Model. arxiv: 2405.04434 [cs.CL]"},{"key":"e_1_3_2_2_12_1","volume-title":"A survey on in-context learning. arXiv preprint arXiv:2301.00234","author":"Dong Qingxiu","year":"2022","unstructured":"Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, and Zhifang Sui. 2022. A survey on in-context learning. arXiv preprint arXiv:2301.00234 (2022)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019","volume":"1084","author":"Fabbri Alexander R.","year":"2019","unstructured":"Alexander R. Fabbri, Irene Li, Tianwei She, Suyi Li, and Dragomir R. Radev. 2019. Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, Anna Korhonen, David R. Traum, and Llu\u00eds M\u00e0rquez (Eds.). Association for Computational Linguistics, 1074--1084."},{"key":"e_1_3_2_2_15_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Fu Yao","year":"2024","unstructured":"Yao Fu, Rameswar Panda, Xinyao Niu, Xiang Yue, Hannaneh Hajishirzi, Yoon Kim, and Hao Peng. 2024. Data Engineering for Scaling Language Models to 128K Context. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net."},{"key":"e_1_3_2_2_16_1","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun Qianyu Guo Meng Wang and Haofen Wang. 2024. Retrieval-Augmented Generation for Large Language Models: A Survey. arxiv: 2312.10997 [cs.CL]"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5409"},{"key":"e_1_3_2_2_18_1","unstructured":"Daya Guo Canwen Xu Nan Duan Jian Yin and Julian McAuley. 2023. LongCoder: A Long-Range Pre-trained Language Model for Code Completion. arxiv: 2306.14893 [cs.SE]"},{"key":"e_1_3_2_2_19_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. In Proceedings of the 28th International Conference on Computational Linguistics, Donia Scott, Nuria Bel, and Chengqing Zong (Eds.). International Committee on Computational Linguistics, Barcelona, Spain (Online), 6609--6625."},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the 2021 Conference of the North American","author":"Huang Luyang","unstructured":"Luyang Huang, Shuyang Cao, Nikolaus Parulian, Heng Ji, and Lu Wang. 2021. Efficient Attentions for Long Document Summarization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, and Yichao Zhou (Eds.). Association for Computational Linguistics, Online, 1419--1436."},{"key":"e_1_3_2_2_21_1","volume-title":"International Conference on Learning Representations.","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard and Edouard Grave. 2021. Distilling Knowledge from Reader to Retriever for Question Answering. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_22_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_2_23_1","volume-title":"G\u00e1bor Melis, and Edward Grefenstette.","author":"Ko\u010disk\u00fd Tom\u00e1\u0161","year":"2017","unstructured":"Tom\u00e1\u0161 Ko\u010disk\u00fd, Jonathan Schwarz, Phil Blunsom, Chris Dyer, Karl Moritz Hermann, G\u00e1bor Melis, and Edward Grefenstette. 2017. The NarrativeQA Reading Comprehension Challenge. arxiv: 1712.07040 [cs.CL]"},{"key":"e_1_3_2_2_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, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems, Vol. 33. 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_25_1","volume-title":"NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following.","author":"Li Dacheng","year":"2023","unstructured":"Dacheng Li, Rulin Shao, Anze Xie, Ying Sheng, Lianmin Zheng, Joseph Gonzalez, Ion Stoica, Xuezhe Ma, and Hao Zhang. 2023a. How Long Can Context Length of Open-Source LLMs truly Promise?. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following."},{"key":"e_1_3_2_2_26_1","unstructured":"Dacheng Li Rulin Shao Anze Xie Ying Sheng Lianmin Zheng Joseph E. Gonzalez Ion Stoica Xuezhe Ma and Hao Zhang. 2023b. How Long Can Open-Source LLMs Truly Promise on Context Length? https:\/\/lmsys.org\/blog\/2023-06-29-longchat"},{"key":"e_1_3_2_2_27_1","unstructured":"Nelson F. Liu Kevin Lin John Hewitt Ashwin Paranjape Michele Bevilacqua Fabio Petroni and Percy Liang. 2023. Lost in the Middle: How Language Models Use Long Contexts. arxiv: 2307.03172 [cs.CL]"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Kun Luo Zheng Liu Shitao Xiao and Kang Liu. 2024. BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models. arxiv: 2402.11573 [cs.CL]","DOI":"10.18653\/v1\/2024.acl-long.180"},{"key":"e_1_3_2_2_29_1","volume-title":"Foundations of machine learning","author":"Mohri Mehryar","unstructured":"Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. 2018. Foundations of machine learning. MIT press."},{"key":"e_1_3_2_2_30_1","unstructured":"Reiichiro Nakano Jacob Hilton Suchir Balaji Jeff Wu Long Ouyang Christina Kim Christopher Hesse Shantanu Jain Vineet Kosaraju William Saunders Xu Jiang Karl Cobbe Tyna Eloundou Gretchen Krueger Kevin Button Matthew Knight Benjamin Chess and John Schulman. 2022. WebGPT: Browser-assisted question-answering with human feedback. arxiv: 2112.09332 [cs.CL]"},{"key":"e_1_3_2_2_31_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/cdn.openai.com\/papers\/gpt-4.pdf."},{"key":"e_1_3_2_2_32_1","volume-title":"YaRN: Efficient Context Window Extension of Large Language Models. In The Twelfth International Conference on Learning Representations.","author":"Peng Bowen","year":"2023","unstructured":"Bowen Peng, Jeffrey Quesnelle, Honglu Fan, and Enrico Shippole. 2023. YaRN: Efficient Context Window Extension of Large Language Models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Lun-Wei Ku","author":"Qian Hongjin","unstructured":"Hongjin Qian, Zheng Liu, Kelong Mao, Yujia Zhou, and Zhicheng Dou. 2024. Grounding Language Model with Chunking-Free In-Context Retrieval. 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, 1298--1311."},{"key":"e_1_3_2_2_34_1","unstructured":"Hongjing Qian Yutao Zhu Zhicheng Dou Haoqi Gu Xinyu Zhang Zheng Liu Ruofei Lai Zhao Cao Jian-Yun Nie and Ji-Rong Wen. 2023. WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus. arxiv: 2304.04358 [cs.CL] https:\/\/arxiv.org\/abs\/2304.04358"},{"key":"e_1_3_2_2_35_1","volume-title":"Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Beck Labash, and Ashwin Gopinath. 2023. Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366 (2023)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Naftali Tishby and Noga Zaslavsky. 2015. Deep Learning and the Information Bottleneck Principle. arxiv: 1503.02406 [cs.LG]","DOI":"10.1109\/ITW.2015.7133169"},{"key":"e_1_3_2_2_37_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_2_38_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00475"},{"key":"e_1_3_2_2_39_1","volume-title":"Fei Xia, Ed H. Chi, Quoc V Le, and Denny Zhou.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed H. Chi, Quoc V Le, and Denny Zhou. 2022. Chain of Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems, Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (Eds.)."},{"key":"e_1_3_2_2_40_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Xu Peng","year":"2023","unstructured":"Peng Xu, Wei Ping, Xianchao Wu, Lawrence McAfee, Chen Zhu, Zihan Liu, Sandeep Subramanian, Evelina Bakhturina, Mohammad Shoeybi, and Bryan Catanzaro. 2023. Retrieval meets Long Context Large Language Models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_41_1","volume-title":"Manning","author":"Yang Zhilin","year":"2018","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. arxiv: 1809.09600 [cs.CL]"},{"key":"e_1_3_2_2_42_1","unstructured":"Peitian Zhang Ninglu Shao Zheng Liu Shitao Xiao Hongjin Qian Qiwei Ye and Zhicheng Dou. 2024. Extending Llama-3's Context Ten-Fold Overnight. arxiv: 2404.19553 [cs.CL]"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709240","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:41:27Z","timestamp":1755358887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709240"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":42,"alternative-id":["10.1145\/3690624.3709240","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709240","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}