{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T23:49:47Z","timestamp":1781048987252,"version":"3.54.1"},"reference-count":100,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206174"],"award-info":[{"award-number":["62206174"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00391","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4101-4113","source":"Crossref","is-referenced-by-count":2,"title":["Why LVLMs are More Prone to Hallucinations in Longer Responses: The Role of Context"],"prefix":"10.1109","author":[{"given":"Ge","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaye","family":"Qian","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajin","family":"Tang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sibei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445463"},{"key":"ref6","article-title":"Videollm: Modeling video sequence with large language models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref10","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Januspro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref13","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01301"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02369"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00139"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018417"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02457"},{"key":"ref23","article-title":"Free-bloom: Zero-shot text-to-video generator with 11 m director and 1 dm animator","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"MVTokenflow: High-quality 4d content generation using multiview token flow","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Huang","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.568"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4246"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01316"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref34","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref36","article-title":"Cityanchor: City-scale 3d visual grounding with multi-modality LLMs","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Li","year":"2025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.687"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00053"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074008"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_26"},{"key":"ref46","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Liu","year":"2023"},{"key":"ref47","author":"Liu","year":"2023","journal-title":"Visual instruction tuning"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref50","article-title":"Paying more attention to image: A training-free method for alleviating hallucination in 1vlms","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25264"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/758"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref54","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref56","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":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref60","first-page":"201","volume-title":"Spatial and Visual PerspectiveTaking via View Rotation and Relation Reasoning for Em-bodied Reference Understanding","author":"Shi","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00274"},{"key":"ref63","article-title":"The devil is in the object boundary: Towards annotation-free instance segmentation using foundation models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shi","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_1"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_13"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1077"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00285"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00914"},{"key":"ref71","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Amber: An llm -free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"An 11 m -free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Measuring multimodal mathematical reasoning with math-vision dataset","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref77","first-page":"25244","article-title":"Discovering influential neuron path in vision transformers","volume-title":"International Conference on Representation Learning","author":"Wang","year":"2025"},{"key":"ref78","article-title":"Toward a stable, fair, and comprehensive evaluation of object hallucination in large visionlanguage models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Wei","year":"2024"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00278"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_35"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00165"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"ref88","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_12"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3592094"},{"key":"ref92","article-title":"How language model hallucinations can snowball","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref93","article-title":"Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models","author":"Zheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00348"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00252"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234002"},{"key":"ref97","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref98","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00433"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"}],"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\/11446078.pdf?arnumber=11446078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:57:54Z","timestamp":1777611474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00391","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}