{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T23:50:05Z","timestamp":1769730605103,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209377","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Beyond Multimodal Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Zhao","sequence":"first","affiliation":[{"name":"Shanghai AI Laboratory,China"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}]},{"given":"Linke","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}]},{"given":"Xiaoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}]},{"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}]},{"given":"Conghui","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}]}],"member":"263","reference":[{"key":"ref1","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models"},{"key":"ref2","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref4","author":"Zhang","year":"2023","journal-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref6","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"ICLR","author":"Liu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref9","author":"Zhou","year":"2023","journal-title":"Analyzing and mitigating object hallucination in large vision-language models"},{"key":"ref10","author":"Zhai","year":"2023","journal-title":"Halle-switch: Rethinking and controlling object existence hallucinations in large vision language models for detailed caption"},{"key":"ref11","author":"Bai","year":"2022","journal-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback"},{"key":"ref12","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2024","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref14","author":"Wang","year":"2023","journal-title":"Evaluation and analysis of hallucination in large vision-language models"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref17","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01274"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref20","article-title":"Sequence to sequence learning with neural networks","volume-title":"NIPS","volume":"27","author":"Sutskever"},{"key":"ref21","author":"Fu","year":"2023","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209377.pdf?arnumber=11209377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:52:58Z","timestamp":1761889978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209377","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}