{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T11:40:43Z","timestamp":1793965243146,"version":"4.8.0"},"reference-count":87,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00067","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"635-646","source":"Crossref","is-referenced-by-count":8,"title":["Mitigating Object Hallucinations via Sentence-Level Early Intervention"],"prefix":"10.1109","author":[{"given":"Shangpin","family":"Peng","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songiao","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Jiang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuotao","family":"Tian","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv:2303.08774"},{"key":"ref2","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization","author":"Bai","year":"2023","journal-title":"Text Reading, and Beyond"},{"key":"ref3","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv:2502.13923"},{"key":"ref4","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024","journal-title":"arXiv preprint arXiv:2404.18930"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"ref6","article-title":"Halc: Object hallucination reduction via adaptive focal-contrast decoding","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2403.00425"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref8","article-title":"Dola: Decoding by contrasting layers improves factuality in large language models","author":"Chuang","year":"2023","journal-title":"arXiv preprint arXiv:2309.03883"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.52202\/075280-2142","article-title":"Instructblip: Towards generalpurpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref11","article-title":"Mask-dpo: Generalizable fine-grained factuality alignment of llms","author":"Gu","year":"2025","journal-title":"arXiv preprint arXiv:2503.02846"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref14","article-title":"Visual perturbation-aware collaborative learning for overcoming the language prior problem","author":"Han","year":"2022","journal-title":"arXiv preprint arXiv:2207.11850"},{"key":"ref15","article-title":"Skip\\n: A simple method to reduce hallucination in large vision-language models","author":"Han","year":"2024","journal-title":"arXiv preprint arXiv:2402.01345"},{"key":"ref16","article-title":"A topic-level self-correctional approach to mitigate hallucinations in mllms","author":"He","year":"2024","journal-title":"arXiv preprint arXiv:2411.17265"},{"key":"ref17","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref18","article-title":"Advancing medical imaging with language models: A journey from n-grams to chatgpt","author":"Hu","year":"2023","journal-title":"arXiv preprint arXiv:2304.04920"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref20","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv:2410.21276"},{"key":"ref21","article-title":"Fgaif: Aligning large vision-language models with fine-grained ai feedback","author":"Jing","year":"2024","journal-title":"arXiv preprint arXiv:2404.05046"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.290"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref25","article-title":"Step-dpo: Step-wise preference optimization for long-chain reasoning of llms","author":"Lai","year":"2024","journal-title":"arXiv preprint arXiv:2406.18629"},{"key":"ref26","article-title":"Volcano: mitigating multimodal hallucination through self-feedback guided revision","author":"Lee","year":"2023","journal-title":"arXiv preprint arXiv:2311.07362"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref28","article-title":"Silkie: Preference distillation for large visual language models","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv:2312.10665"},{"key":"ref29","article-title":"Mini-gemini: Mining the potential of multi-modality vision language models","author":"Li","year":"2023","journal-title":"arXiv:2403.18814"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.398"},{"key":"ref31","article-title":"Flame: Factualityaware alignment for large language models","author":"Lin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2306.14565"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref35","article-title":"Llavanext: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref36","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2402.00253"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref38","article-title":"Typicalnessaware learning for failure detection","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2411.01981"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref40","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv:1711.05101"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3946"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01251"},{"key":"ref44","article-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_23"},{"key":"ref46","article-title":"Smaug: Fixing failure modes of preference optimisation with dpo-positive","author":"Pal","year":"2024","journal-title":"arXiv preprint arXiv:2402.13228"},{"key":"ref47","article-title":"Omni-dpo: A dualperspective paradigm for dynamic preference learning of llms","author":"Peng","year":"2025","journal-title":"arXiv preprint arXiv:2506.10054"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01942"},{"key":"ref49","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref53","article-title":"A survey of hallucination in large foundation models","author":"Rawte","year":"2023","journal-title":"arXiv preprint arXiv:2309.05922"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref56","article-title":"Data-augmented phrase-level alignment for mitigating object hallucination","author":"Sarkar","year":"2024","journal-title":"arXiv preprint arXiv:2405.18654"},{"key":"ref57","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_9"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref60","article-title":"Fine-tuning language models for factuality","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tian","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00436"},{"key":"ref62","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref63","article-title":"Amber: An llm-free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2311.07397"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01381"},{"key":"ref65","article-title":"Qwen2\u2013vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2409.12191"},{"key":"ref66","article-title":"Noiseboost: Alleviating hallucination with noise perturbation for multimodal large language models","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv:2405.20081"},{"key":"ref67","article-title":"Overcoming language priors in visual question answering via distinguishing superficially similar instances","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Wu","year":"2022"},{"key":"ref68","article-title":"Embodied task planning with large language models","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv:2307.01848"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34744"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.67"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33001"},{"key":"ref72","article-title":"An improved baseline for reasoning segmentation with large language model","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2312.17240"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01843"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02209"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"ref77","article-title":"Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv:2405.17220"},{"key":"ref78","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv:2308.02490"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.633"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0823"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1049\/cvi2.12268"},{"key":"ref82","article-title":"Beyond hallucinations: Enhancing lvlms through hallucination-aware direct preference optimization","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv:2311.16839"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"ref84","article-title":"Lyra: An efficient and speech-centric framework for omni-cognition","author":"Zhong","year":"2024","journal-title":"arXiv preprint arXiv:2412.09501"},{"key":"ref85","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2023","journal-title":"arXiv preprint arXiv:2310.00754"},{"key":"ref86","article-title":"Aligning modalities in vision large language models via preference fine-tuning","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv:2402.11411"},{"key":"ref87","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv:2304.10592"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445989.pdf?arnumber=11445989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:57:37Z","timestamp":1777611457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00067","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}