{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:47:19Z","timestamp":1783439239749,"version":"3.54.6"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887699","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":10,"title":["CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation"],"prefix":"10.1109","author":[{"given":"Yue","family":"Jiang","sequence":"first","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingkang","family":"Yang","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingcheng","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunli","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79942-9_2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28038"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.364"},{"key":"ref7","article-title":"Bottom-up and top-down attention for image captioning and vqa","author":"Anderson","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2022.3171661"},{"key":"ref11","article-title":"Mitigating hallucination in visual language models with visual supervision","author":"Chen","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53302-0_3"},{"key":"ref13","first-page":"36","article-title":"Improving clip training with language rewrites","author":"Fan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72353-7_22"},{"key":"ref15","article-title":"Chain of thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"no journal"},{"key":"ref16","author":"Chen","year":"2024","journal-title":"Cod, towards an interpretable medical agent using chain of diagnosis"},{"key":"ref17","article-title":"Enhancing depression diagnosis with chain-of-thought prompting","author":"Shi","year":"2024","journal-title":"no journal"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2015.08.008"},{"key":"ref19","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref20","year":"2023","journal-title":"GPT-4V(vision) system card"},{"key":"ref21","article-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2019","journal-title":"no journal"},{"key":"ref22","first-page":"228","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"Satanjeev","year":"2005","journal-title":"ACL-2005"},{"key":"ref23","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Meeting of the Association for Computational Linguistics,Meeting of the Association for Computational Linguistics","author":"Lin"},{"key":"ref24","author":"Chen","year":"2024","journal-title":"Detecting and evaluating medical hallucinations in large vision language models"},{"key":"ref25","year":"2024","journal-title":"Gemini: A family of highly capable multimodal models"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref28","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","author":"Li","year":"2023"},{"key":"ref29","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00925-4"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887699.pdf?arnumber=10887699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:30Z","timestamp":1774416270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887699","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}