{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:05:08Z","timestamp":1784138708612,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":32,"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":["62276002"],"award-info":[{"award-number":["62276002"]}]},{"name":"Zhongguancun Academy","award":["C20250513"],"award-info":[{"award-number":["C20250513"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809930","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3753-3758","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EviRAG: Evidence-Guided Retrieval-Augmented Generation for Medical Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5915-4448","authenticated-orcid":false,"given":"Yiyang","family":"Gu","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0078-5851","authenticated-orcid":false,"given":"Jiayue","family":"Fan","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5204-3184","authenticated-orcid":false,"given":"Kaili","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8643-7151","authenticated-orcid":false,"given":"Bohan","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9589-6232","authenticated-orcid":false,"given":"Binqi","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1873-6073","authenticated-orcid":false,"given":"Zequn","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhongguancun Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8583-4789","authenticated-orcid":false,"given":"Zhiping","family":"Xiao","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9567-159X","authenticated-orcid":false,"given":"Rong-Cheng","family":"Tu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7987-3714","authenticated-orcid":false,"given":"Xiao","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9809-3430","authenticated-orcid":false,"given":"Ming","family":"Zhang","sequence":"additional","affiliation":[{"name":"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":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.460"},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PmLR, 1597-1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020a. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PmLR, 1597-1607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"e_1_3_2_1_5_1","volume-title":"Dola: Decoding by contrasting layers improves factuality in large language models. arXiv preprint arXiv:2309.03883","author":"Chuang Yung-Sung","year":"2023","unstructured":"Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, and Pengcheng He. 2023. Dola: Decoding by contrasting layers improves factuality in large language models. arXiv preprint arXiv:2309.03883 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"e_1_3_2_1_7_1","first-page":"209","article-title":"Retrieval-based chest x-ray report generation using a pre-trained contrastive language-image model","author":"Endo Mark","year":"2021","unstructured":"Mark Endo, Rayan Krishnan, Viswesh Krishna, Andrew Y Ng, and Pranav Rajpurkar. 2021. Retrieval-based chest x-ray report generation using a pre-trained contrastive language-image model. In Machine Learning for Health. PMLR, 209-219.","journal-title":"Machine Learning for Health. PMLR"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.939"},{"key":"e_1_3_2_1_9_1","volume-title":"Meddr: Diagnosis-guided bootstrapping for large-scale medical vision-language learning. arXiv preprint arXiv:2404.15127","author":"He Sunan","year":"2024","unstructured":"Sunan He, Yuxiang Nie, Zhixuan Chen, Zhiyuan Cai, Hongmei Wang, Shu Yang, and Hao Chen. 2024. Meddr: Diagnosis-guided bootstrapping for large-scale medical vision-language learning. arXiv preprint arXiv:2404.15127, Vol. 1, 3 (2024), 6."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"e_1_3_2_1_12_1","volume-title":"Du Nguyen Duong, Tan Bui, Pierre Chambon, Yuhao Zhang, Matthew P Lungren, Andrew Y Ng, et al.","author":"Jain Saahil","year":"2021","unstructured":"Saahil Jain, Ashwin Agrawal, Adriel Saporta, Steven QH Truong, Du Nguyen Duong, Tan Bui, Pierre Chambon, Yuhao Zhang, Matthew P Lungren, Andrew Y Ng, et al., 2021. Radgraph: Extracting clinical entities and relations from radiology reports. arXiv preprint arXiv:2106.14463 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240"},{"key":"e_1_3_2_1_14_1","volume-title":"a de-identified publicly available database of chest radiographs with free-text reports. Scientific data","author":"Johnson Alistair EW","year":"2019","unstructured":"Alistair EW Johnson, Tom J Pollard, Seth J Berkowitz, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Roger G Mark, and Steven Horng. 2019. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Scientific data, Vol. 6, 1 (2019), 317."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"e_1_3_2_1_17_1","volume-title":"Hybrid retrieval-generation reinforced agent for medical image report generation. Advances in neural information processing systems","author":"Li Yuan","year":"2018","unstructured":"Yuan Li, Xiaodan Liang, Zhiting Hu, and Eric P Xing. 2018. Hybrid retrieval-generation reinforced agent for medical image report generation. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_18_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"e_1_3_2_1_20_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_21_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1674"},{"key":"e_1_3_2_1_23_1","volume-title":"CheXbert: combining automatic labelers and expert annotations for accurate radiology report labeling using BERT. arXiv preprint arXiv:2004.09167","author":"Smit Akshay","year":"2020","unstructured":"Akshay Smit, Saahil Jain, Pranav Rajpurkar, Anuj Pareek, Andrew Y Ng, and Matthew P Lungren. 2020. CheXbert: combining automatic labelers and expert annotations for accurate radiology report labeling using BERT. arXiv preprint arXiv:2004.09167 (2020)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.28"},{"key":"e_1_3_2_1_25_1","volume-title":"Sequence to sequence learning with neural networks. Advances in neural information processing systems","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03302-1"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2300138"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"e_1_3_2_1_29_1","volume-title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models. In The Thirteenth International Conference on Learning Representations.","author":"Xia Peng","year":"2025","unstructured":"Peng Xia, Kangyu Zhu, Haoran Li, Tianze Wang, Weijia Shi, Sheng Wang, Linjun Zhang, James Zou, and Huaxiu Yao. 2025. MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.62"},{"key":"e_1_3_2_1_31_1","volume-title":"When and why vision-language models behave like bags-of-words, and what to do about it? arXiv preprint arXiv:2210.01936","author":"Yuksekgonul Mert","year":"2022","unstructured":"Mert Yuksekgonul, Federico Bianchi, Pratyusha Kalluri, Dan Jurafsky, and James Zou. 2022. When and why vision-language models behave like bags-of-words, and what to do about it? arXiv preprint arXiv:2210.01936 (2022)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.350"}],"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":"2026-07-15T17:18:38Z","timestamp":1784135918000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809930"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":32,"alternative-id":["10.1145\/3805712.3809930","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809930","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"}}]}}