{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:08:08Z","timestamp":1784138888756,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809540","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"1141-1151","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3658-9147","authenticated-orcid":false,"given":"Peiyang","family":"Liu","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Software Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1742-7866","authenticated-orcid":false,"given":"Ziqiang","family":"Cui","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2316-8320","authenticated-orcid":false,"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3684-4550","authenticated-orcid":false,"given":"Di","family":"Liang","sequence":"additional","affiliation":[{"name":"Tencent Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9331-4716","authenticated-orcid":false,"given":"Wei","family":"Ye","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Software Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000877"},{"key":"e_1_3_2_1_3_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Asai Akari","year":"2024","unstructured":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=hSyW5go0v8"},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Massimiliano Ciaramita, Jacob Eisenstein, Kuzman Ganchev, Jonathan Herzig, et al.","author":"Bohnet Bernd","year":"2022","unstructured":"Bernd Bohnet, Vinh Q Tran, Pat Verga, Roee Aharoni, Daniel Andor, Livio Baldini Soares, Massimiliano Ciaramita, Jacob Eisenstein, Kuzman Ganchev, Jonathan Herzig, et al., 2022. Attributed question answering: Evaluation and modeling for attributed large language models. arXiv preprint arXiv:2212.08037 (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"Anurag Ajay, Alexander C Li, Adrien Bardes, Suzanne Petryk, Oscar Ma nas, Zhiqiu Lin, Anas Mahmoud, Bargav Jayaraman, et al.","author":"Bordes Florian","year":"2024","unstructured":"Florian Bordes, Richard Yuanzhe Pang, Anurag Ajay, Alexander C Li, Adrien Bardes, Suzanne Petryk, Oscar Ma nas, Zhiqiu Lin, Anas Mahmoud, Bargav Jayaraman, et al., 2024. An introduction to vision-language modeling. arXiv preprint arXiv:2405.17247 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"HTML for the world wide web","author":"Castro Elizabeth","unstructured":"Elizabeth Castro. 2003. HTML for the world wide web. Peachpit Press."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3675392"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Zhiwei Chen Yupeng Hu Zhiheng Fu Zixu Li Jiale Huang Qinlei Huang and Yinwei Wei. 2026. INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval. In Fortieth AAAI Conference on Artificial Intelligence Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence Sixteenth Symposium on Educational Advances in Artificial Intelligence AAAI 2026 Singapore January 20-27 2026 Sven Koenig Chad Jenkins and Matthew E. Taylor (Eds.). AAAI Press 20463-20471. doi:10.1609\/AAAI.V40I25.39181","DOI":"10.1609\/AAAI.V40I25.39181"},{"key":"e_1_3_2_1_10_1","unstructured":"Jon Duckett and Jens Schl\u00fcter. 2011. Html & Css. Wiley."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.929"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.398"},{"key":"e_1_3_2_1_13_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, Yixin Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 2023a. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, Vol. 2, 1 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Hands-On Selenium WebDriver with Java. '' O'Reilly Media","author":"Garc\u00eda Boni","unstructured":"Boni Garc\u00eda. 2022. Hands-On Selenium WebDriver with Java. '' O'Reilly Media, Inc.''."},{"key":"e_1_3_2_1_15_1","first-page":"1158","article-title":"Wikipedia survey-overview of results","volume":"8","author":"Glott Ruediger","year":"2010","unstructured":"Ruediger Glott, Philipp Schmidt, and Rishab Ghosh. 2010. Wikipedia survey-overview of results. United Nations University: Collaborative Creativity Group, Vol. 8 (2010), 1158-1178.","journal-title":"United Nations University: Collaborative Creativity Group"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.COLING-MAIN.580"},{"key":"e_1_3_2_1_18_1","volume-title":"Refine: Composed video retrieval via shared and differential semantics enhancement. ACM Transactions on Multimedia Computing, Communications and Applications","author":"Hu Yupeng","year":"2026","unstructured":"Yupeng Hu, Zixu Li, Zhiwei Chen, Qinlei Huang, Zhiheng Fu, Mingzhu Xu, and Liqiang Nie. 2026. Refine: Composed video retrieval via shared and differential semantics enhancement. ACM Transactions on Multimedia Computing, Communications and Applications (2026)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_1_20_1","volume-title":"Sung Ju Hwang, and Jong C Park","author":"Jeong Soyeong","year":"2024","unstructured":"Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C Park. 2024. Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity. arXiv preprint arXiv:2403.14403 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Andrea Madotto, and Pascale Fung.","author":"Ji Ziwei","year":"2023","unstructured":"Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM computing surveys, Vol. 55, 12 (2023), 1-38."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"e_1_3_2_1_23_1","volume-title":"Source-aware training enables knowledge attribution in language models. arXiv preprint arXiv:2404.01019","author":"Khalifa Muhammad","year":"2024","unstructured":"Muhammad Khalifa, David Wadden, Emma Strubell, Honglak Lee, Lu Wang, Iz Beltagy, and Hao Peng. 2024. Source-aware training enables knowledge attribution in language models. arXiv preprint arXiv:2404.01019 (2024)."},{"key":"e_1_3_2_1_24_1","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."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Bo Li Tian Tian Zhenghua Xu Hao Cheng Shikun Zhang and Wei Ye. 2026 a. Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG. In Fortieth AAAI Conference on Artificial Intelligence Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence Sixteenth Symposium on Educational Advances in Artificial Intelligence AAAI 2026 Singapore January 20-27 2026. AAAI Press 31527-31535.","DOI":"10.1609\/aaai.v40i37.40418"},{"key":"e_1_3_2_1_26_1","unstructured":"Bo Li Mingda Wang Gexiang Fang Shikun Zhang and Wei Ye. 2026 b. Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning. arXiv:2604.11407 [cs.CL] https:\/\/arxiv.org\/abs\/2604.11407"},{"key":"e_1_3_2_1_27_1","unstructured":"Bo Li Mingda Wang Shikun Zhang and Wei Ye. 2026 c. Instruction Data Selection via Answer Divergence. arXiv:2604.10448 [cs.CL] https:\/\/arxiv.org\/abs\/2604.10448"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Bo Li Shikun Zhang and Wei Ye. 2026 e. Data Selection for Multi-turn Dialogue Instruction Tuning. arXiv:2604.07892 [cs.CL] https:\/\/arxiv.org\/abs\/2604.07892","DOI":"10.18653\/v1\/2026.findings-acl.130"},{"key":"e_1_3_2_1_29_1","unstructured":"Xiping Li and Jianghong Ma. 2025. AIMCoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645573"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3789264"},{"key":"e_1_3_2_1_32_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123335"},{"key":"e_1_3_2_1_34_1","unstructured":"Peiyang Liu Zhirui Chen Xi Wang Di Liang Youru Li Zhi Cai and Wei Ye. 2026. Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories. arXiv:2604.11365 [cs.AI] https:\/\/arxiv.org\/abs\/2604.11365"},{"key":"e_1_3_2_1_35_1","volume-title":"Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft. arXiv preprint arXiv:2510.07728","author":"Liu Peiyang","year":"2025","unstructured":"Peiyang Liu, Ziqiang Cui, Di Liang, and Wei Ye. 2025a. Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft. arXiv preprint arXiv:2510.07728 (2025)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.292"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730066"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481909"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.13"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the 29th international conference on computational linguistics. 2210-2219","author":"Liu Peiyang","year":"2022","unstructured":"Peiyang Liu, Xiangyu Xi, Wei Ye, and Shikun Zhang. 2022. Label smoothing for text mining. In Proceedings of the 29th international conference on computational linguistics. 2210-2219."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615146"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207311"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1456"},{"key":"e_1_3_2_1_44_1","volume-title":"Masked Diffusion Generative Recommendation. arXiv preprint arXiv:2601.19501","author":"Mu Lingyu","year":"2026","unstructured":"Lingyu Mu, Hao Deng, Haibo Xing, Jinxin Hu, Yu Zhang, Xiaoyi Zeng, and Jing Zhang. 2026. Masked Diffusion Generative Recommendation. arXiv preprint arXiv:2601.19501 (2026)."},{"key":"e_1_3_2_1_45_1","volume-title":"RAG in health care: a novel framework for improving communication and decision-making by addressing LLM limitations. Nejm Ai","author":"Yan Ng Karen Ka","year":"2025","unstructured":"Karen Ka Yan Ng, Izuki Matsuba, and Peter Chengming Zhang. 2025. RAG in health care: a novel framework for improving communication and decision-making by addressing LLM limitations. Nejm Ai, Vol. 2, 1 (2025), AIra2400380."},{"key":"e_1_3_2_1_46_1","volume-title":"Chain-of-action: Faithful and multimodal question answering through large language models. arXiv preprint arXiv:2403.17359","author":"Pan Zhenyu","year":"2024","unstructured":"Zhenyu Pan, Haozheng Luo, Manling Li, and Han Liu. 2024. Chain-of-action: Faithful and multimodal question answering through large language models. arXiv preprint arXiv:2403.17359 (2024)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00486"},{"key":"e_1_3_2_1_48_1","volume-title":"A survey of hallucination in large foundation models. arXiv preprint arXiv:2309.05922","author":"Rawte Vipula","year":"2023","unstructured":"Vipula Rawte, Amit Sheth, and Amitava Das. 2023. A survey of hallucination in large foundation models. arXiv preprint arXiv:2309.05922 (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.70036"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.ACL-LONG.702"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Ryota Tanaka Kyosuke Nishida Kosuke Nishida Taku Hasegawa Itsumi Saito and Kuniko Saito. 2023. SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images. In AAAI.","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.ACL-LONG.557"},{"key":"e_1_3_2_1_53_1","volume-title":"Financial analysis: Intelligent financial data analysis system based on llm-rag. arXiv preprint arXiv:2504.06279","author":"Wang Jingru","year":"2025","unstructured":"Jingru Wang, Wen Ding, and Xiaotong Zhu. 2025b. Financial analysis: Intelligent financial data analysis system based on llm-rag. arXiv preprint arXiv:2504.06279 (2025)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.14342"},{"key":"e_1_3_2_1_55_1","volume-title":"DeepSeek-OCR: Contexts Optical Compression. arXiv preprint arXiv:2510.18234","author":"Wei Haoran","year":"2025","unstructured":"Haoran Wei, Yaofeng Sun, and Yukun Li. 2025. DeepSeek-OCR: Contexts Optical Compression. arXiv preprint arXiv:2510.18234 (2025)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63646-2_29"},{"key":"e_1_3_2_1_57_1","unstructured":"Haibo Xing Hao Deng Yucheng Mao Lingyu Mu Jinxin Hu Yi Xu Hao Zhang Jiahao Wang Shizhun Wang Yu Zhang et al. 2025. Reg4rec: Reasoning-enhanced generative model for large-scale recommendation systems. arXiv preprint arXiv:2508.15308 (2025)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.372"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1312"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.NAACL-LONG.346"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3850"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_63_1","volume-title":"Hint: Composed image retrieval with dual-path compositional contextualized network.","author":"Zhang Mingyu","year":"2026","unstructured":"Mingyu Zhang, Zixu Li, Zhiwei Chen, Zhiheng Fu, Xiaowei Zhu, Jiajia Nie, Yinwei Wei, and Yupeng Hu. 2026. Hint: Composed image retrieval with dual-path compositional contextualized network. (2026), 13002-13006."},{"key":"e_1_3_2_1_64_1","volume-title":"Raft: Adapting language model to domain specific rag. arXiv preprint arXiv:2403.10131","author":"Zhang Tianjun","year":"2024","unstructured":"Tianjun Zhang, Shishir G Patil, Naman Jain, Sheng Shen, Matei Zaharia, Ion Stoica, and Joseph E Gonzalez. 2024b. Raft: Adapting language model to domain specific rag. arXiv preprint arXiv:2403.10131 (2024)."},{"key":"e_1_3_2_1_65_1","volume-title":"Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473","author":"Zhao Penghao","year":"2024","unstructured":"Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, Jie Jiang, and Bin Cui. 2024. Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473 (2024)."},{"key":"e_1_3_2_1_66_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:24:31Z","timestamp":1784136271000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":66,"alternative-id":["10.1145\/3805712.3809540","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809540","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}