{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T18:00:17Z","timestamp":1776103217449,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476201"],"award-info":[{"award-number":["62476201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222203"],"award-info":[{"award-number":["62222203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Meituan and the New Cornerstone Science Foundation through the XPLORER PRIZE"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3599076","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:48:19Z","timestamp":1755197299000},"page":"7380-7391","source":"Crossref","is-referenced-by-count":4,"title":["Mitigating Hallucinations in Large Vision-Language Models via Reasoning Uncertainty-Guided Refinement"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-012X","authenticated-orcid":false,"given":"Shenshen","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"given":"Wenxin","family":"Meng","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"given":"Chong","family":"Peng","sequence":"additional","affiliation":[{"name":"Meituan, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 22nd Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref2","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3253054"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3571946"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref10","article-title":"Aligning large multi-modal model with robust instruction tuning","author":"Liu","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref12","first-page":"7824","article-title":"HALC: Object hallucination reduction via adaptive focal-contrast decoding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00150"},{"key":"ref16","first-page":"31450","article-title":"Causal interpretation of self-attention in pre-trained transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rohekar","year":"2023"},{"key":"ref17","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref18","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90 ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3428317"},{"key":"ref20","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 23rd Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref21","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3396272"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251104"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045530"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306738"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref28","article-title":"Shikra: Unleashing multimodal LLMs referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref33","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"Proc. 21th Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_12"},{"key":"ref35","article-title":"Aligning large multi-modal model with robust instruction tuning","author":"Liu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.414"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53302-0_3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213315"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref41","volume-title":"Subjective Logic - A Formalism for Reasoning Under Uncertainty","author":"Jsang","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-44792-4"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612244"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01194"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01395-y"},{"key":"ref46","article-title":"How language model hallucinations can snowball","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Zhang","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref49","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref51","article-title":"DoLa: Decoding by contrasting layers improves factuality in large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Chuang","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref54","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11125489.pdf?arnumber=11125489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:53Z","timestamp":1761153953000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11125489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3599076","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}