{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:08:49Z","timestamp":1784138929378,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":49,"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"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62507010"],"award-info":[{"award-number":["62507010"]}]},{"name":"China Postdoctoral Science Foundation","award":["2024M760725"],"award-info":[{"award-number":["2024M760725"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["2408085QF212"],"award-info":[{"award-number":["2408085QF212"]}]},{"name":"Anhui Postdoctoral Scientific Research Program Foundation","award":["2025A1027"],"award-info":[{"award-number":["2025A1027"]}]},{"name":"Anhui Provincial Higher Education Digital Transformation Project","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]},{"name":"Opening Project of Key Laboratory of Mental Health and Cognitive Science (South China Normal University)","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809664","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"2600-2610","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Good Ranks Follow Good Answers: Unsupervised Answer-Driven Reranking for Multimodal Document QA"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6256-8554","authenticated-orcid":false,"given":"Keyu","family":"Zhu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China and Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, -\u9009\u62e9-, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3905-9352","authenticated-orcid":false,"given":"Shuanghong","family":"Shen","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China and Guangdong Key Laboratory of Mental Health and Cognitive Science, South China Normal University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9744-220X","authenticated-orcid":false,"given":"Xianquan","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5335-2470","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, -\u9009\u62e9-, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9202-7678","authenticated-orcid":false,"given":"Shijin","family":"Wang","sequence":"additional","affiliation":[{"name":"iFLYTEK AI Research & State Key Laboratory of Cognitive Intelligence, iFLYTEK, Co., Ltd, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-5550","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1661-0420","authenticated-orcid":false,"given":"Zhenya","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.861"},{"key":"e_1_3_2_1_2_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.131"},{"key":"e_1_3_2_1_4_1","volume-title":"[n.d.]. Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen Zhe","year":"2025","unstructured":"Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, et al., [n.d.]. Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling, 2025. URL https:\/\/arxiv.org\/abs\/2412.05271 ([n.d.])."},{"key":"e_1_3_2_1_5_1","volume-title":"M3docrag: Multi-modal retrieval is what you need for multi-page multi-document understanding. arXiv preprint arXiv:2411.04952","author":"Cho Jaemin","year":"2024","unstructured":"Jaemin Cho, Debanjan Mahata, Ozan Irsoy, Yujie He, and Mohit Bansal. 2024. M3docrag: Multi-modal retrieval is what you need for multi-page multi-document understanding. arXiv preprint arXiv:2411.04952 (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1264"},{"key":"e_1_3_2_1_7_1","volume-title":"Colpali: Efficient document retrieval with vision language models. arXiv preprint arXiv:2407.01449","author":"Faysse Manuel","year":"2024","unstructured":"Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, C\u00e9line Hudelot, and Pierre Colombo. 2024. Colpali: Efficient document retrieval with vision language models. arXiv preprint arXiv:2407.01449 (2024)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.194"},{"key":"e_1_3_2_1_9_1","volume-title":"MDocAgent: A multi-modal multi-agent framework for document understanding [J\/OL]. arXiv preprint arXiv:2503.13964","author":"SW HAN, P XIA, RY ZHANG","year":"2025","unstructured":"SW HAN, P XIA, RY ZHANG, et al., 2025. MDocAgent: A multi-modal multi-agent framework for document understanding [J\/OL]. arXiv preprint arXiv:2503.13964 (2025)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2145"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018699"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_13_1","volume-title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity. In International Conference on Representation Learning, B. Kim, Y. Yue, S. Chaudhuri, K. Fragkiadaki, M. Khan, and Y. Sun (Eds.)","volume":"2024","author":"Kirk Robert","year":"2024","unstructured":"Robert Kirk, Ishita Mediratta, Christoforos Nalmpantis, Jelena Luketina, Eric Hambro, Edward Grefenstette, and Roberta Raileanu. 2024. Understanding the Effects of RLHF on LLM Generalisation and Diversity. In International Conference on Representation Learning, B. Kim, Y. Yue, S. Chaudhuri, K. Fragkiadaki, M. Khan, and Y. Sun (Eds.), Vol. 2024. 20620-20653. https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2024\/file\/5a68d05006d5b05dd9463dd9c0219db0-Paper-Conference.pdf"},{"key":"e_1_3_2_1_14_1","volume-title":"Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems. arXiv preprint arXiv:2510.24476","author":"Li Yihan","year":"2025","unstructured":"Yihan Li, Xiyuan Fu, Ghanshyam Verma, Paul Buitelaar, and Mingming Liu. 2025. Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems. arXiv preprint arXiv:2510.24476 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.301"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00197"},{"key":"e_1_3_2_1_17_1","volume-title":"Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Short. arXiv preprint arXiv:2510.08985","author":"Lu Xuan","year":"2025","unstructured":"Xuan Lu, Haohang Huang, Rui Meng, Yaohui Jin, Wenjun Zeng, and Xiaoyu Shen. 2025. Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Short. arXiv preprint arXiv:2510.08985 (2025)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1456"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3041"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_1_21_1","volume-title":"Srimat T Chakradhar, and Sennur Ulukus.","author":"Mortaheb Matin","year":"2025","unstructured":"Matin Mortaheb, Mohammad A Amir Khojastepour, Srimat T Chakradhar, and Sennur Ulukus. 2025. Re-ranking the context for multimodal retrieval augmented generation. arXiv preprint arXiv:2501.04695 (2025)."},{"key":"e_1_3_2_1_22_1","volume-title":"Ngrpo: Negative-enhanced group relative policy optimization. arXiv preprint arXiv:2509.18851","author":"Nan Gongrui","year":"2025","unstructured":"Gongrui Nan, Siye Chen, Jing Huang, Mengyu Lu, Dexun Wang, Chunmei Xie, Weiqi Xiong, Xianzhou Zeng, Qixuan Zhou, Yadong Li, et al., 2025. Ngrpo: Negative-enhanced group relative policy optimization. arXiv preprint arXiv:2509.18851 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Jimmy Lin. 2019. Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"Meet Raval, and Dhvani Upadhyay.","author":"Pandit Tejul","year":"2025","unstructured":"Tejul Pandit, Sakshi Mahendru, Meet Raval, and Dhvani Upadhyay. 2025. The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models. arXiv preprint arXiv:2512.16236 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"Lei Fang, and Ji-Rong Wen.","author":"Song Huatong","year":"2025","unstructured":"Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, and Ji-Rong Wen. 2025. R1-searcher: Incentivizing the search capability in llms via reinforcement learning. arXiv preprint arXiv:2503.05592 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation. arXiv preprint arXiv:2505.07233","author":"Sun Jiashuo","year":"2025","unstructured":"Jiashuo Sun, Xianrui Zhong, Sizhe Zhou, and Jiawei Han. 2025b. DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation. arXiv preprint arXiv:2505.07233 (2025)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_2_1_29_1","volume-title":"Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation. arXiv preprint arXiv:2510.09733","author":"Sun Yubo","year":"2025","unstructured":"Yubo Sun, Chunyi Peng, Yukun Yan, Shi Yu, Zhenghao Liu, Chi Chen, Zhiyuan Liu, and Maosong Sun. 2025a. VisRAG 2.0: Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation. arXiv preprint arXiv:2510.09733 (2025)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109834"},{"key":"e_1_3_2_1_31_1","volume-title":"Benefits and pitfalls of reinforcement learning for language model planning: a theoretical perspective. arXiv preprint arXiv:2509.22613","author":"Wang Siwei","year":"2025","unstructured":"Siwei Wang, Yifei Shen, Haoran Sun, Shi Feng, Shang-Hua Teng, Li Dong, Yaru Hao, and Wei Chen. 2025. Benefits and pitfalls of reinforcement learning for language model planning: a theoretical perspective. arXiv preprint arXiv:2509.22613 (2025)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.108"},{"key":"e_1_3_2_1_33_1","volume-title":"Multimodal reranking for knowledge-intensive visual question answering. arXiv preprint arXiv:2407.12277","author":"Wen Haoyang","year":"2024","unstructured":"Haoyang Wen, Honglei Zhuang, Hamed Zamani, Alexander Hauptmann, and Michael Bendersky. 2024. Multimodal reranking for knowledge-intensive visual question answering. arXiv preprint arXiv:2407.12277 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval. arXiv preprint arXiv:2506.12364","author":"Xu Mingjun","year":"2025","unstructured":"Mingjun Xu, Jinhan Dong, Jue Hou, Zehui Wang, Sihang Li, Zhifeng Gao, Renxin Zhong, and Hengxing Cai. 2025. MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval. arXiv preprint arXiv:2506.12364 (2025)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00229"},{"key":"e_1_3_2_1_36_1","volume-title":"Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800","author":"Yao Yuan","year":"2024","unstructured":"Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, et al., 2024. Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents. In International Conference on Representation Learning, Y. Yue, A. Garg, N. Peng, F. Sha, and R. Yu (Eds.)","volume":"2025","author":"Yu Shi","year":"2025","unstructured":"Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, and Maosong Sun. 2025. VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents. In International Conference on Representation Learning, Y. Yue, A. Garg, N. Peng, F. Sha, and R. Yu (Eds.), Vol. 2025. 21074-21098. https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2025\/file\/3640a1997a4c9571cea9db2c82e1fc35-Paper-Conference.pdf"},{"key":"e_1_3_2_1_38_1","volume-title":"Self-adaptive Multimodal Retrieval-Augmented Generation. arXiv preprint arXiv:2410.11321","author":"Zhai Wenjia","year":"2024","unstructured":"Wenjia Zhai. 2024. Self-adaptive Multimodal Retrieval-Augmented Generation. arXiv preprint arXiv:2410.11321 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Vision-r1: Evolving human-free alignment in large vision-language models via vision-guided reinforcement learning. arXiv preprint arXiv:2503.18013","author":"Zhan Yufei","year":"2025","unstructured":"Yufei Zhan, Yousong Zhu, Shurong Zheng, Hongyin Zhao, Fan Yang, Ming Tang, and Jinqiao Wang. 2025. Vision-r1: Evolving human-free alignment in large vision-language models via vision-guided reinforcement learning. arXiv preprint arXiv:2503.18013 (2025)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3767695.3769496"},{"key":"e_1_3_2_1_41_1","volume-title":"R1-vl: Learning to reason with multimodal large language models via step-wise group relative policy optimization. arXiv preprint arXiv:2503.12937","author":"Zhang Jingyi","year":"2025","unstructured":"Jingyi Zhang, Jiaxing Huang, Huanjin Yao, Shunyu Liu, Xikun Zhang, Shijian Lu, and Dacheng Tao. 2025b. R1-vl: Learning to reason with multimodal large language models via step-wise group relative policy optimization. arXiv preprint arXiv:2503.12937 (2025)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.125"},{"key":"e_1_3_2_1_43_1","volume-title":"Edge-grpo: Entropy-driven grpo with guided error correction for advantage diversity. arXiv preprint arXiv:2507.21848","author":"Zhang Xingjian","year":"2025","unstructured":"Xingjian Zhang, Siwei Wen, Wenjun Wu, and Lei Huang. 2025d. Edge-grpo: Entropy-driven grpo with guided error correction for advantage diversity. arXiv preprint arXiv:2507.21848 (2025)."},{"key":"e_1_3_2_1_44_1","volume-title":"Diagramqg: A dataset for generating concept-focused questions from diagrams. arXiv e-prints","author":"Zhang Xinyu","year":"2024","unstructured":"Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang, Wenjun Wu, Bo Li, Shaowei Wang, and Jun Liu. 2024. Diagramqg: A dataset for generating concept-focused questions from diagrams. arXiv e-prints (2024), arXiv-2411."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.165"},{"key":"e_1_3_2_1_46_1","volume-title":"R1-Zero's'' Aha Moment'' in Visual Reasoning on a 2B Non-SFT Model. arXiv preprint arXiv:2503.05132","author":"Zhou Hengguang","year":"2025","unstructured":"Hengguang Zhou, Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, and Cho-Jui Hsieh. 2025. R1-Zero's'' Aha Moment'' in Visual Reasoning on a 2B Non-SFT Model. arXiv preprint arXiv:2503.05132 (2025)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548422"},{"key":"e_1_3_2_1_48_1","volume-title":"Rank-r1: Enhancing reasoning in llm-based document rerankers via reinforcement learning. arXiv preprint arXiv:2503.06034","author":"Zhuang Shengyao","year":"2025","unstructured":"Shengyao Zhuang, Xueguang Ma, Bevan Koopman, Jimmy Lin, and Guido Zuccon. 2025. Rank-r1: Enhancing reasoning in llm-based document rerankers via reinforcement learning. arXiv preprint arXiv:2503.06034 (2025)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657813"}],"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":"2026-07-15T17:25:08Z","timestamp":1784136308000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809664"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":49,"alternative-id":["10.1145\/3805712.3809664","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809664","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"}}]}}