{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:08Z","timestamp":1777890188288,"version":"3.51.4"},"reference-count":67,"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\/iccv51701.2025.00244","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2534-2544","source":"Crossref","is-referenced-by-count":0,"title":["Inter: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling"],"prefix":"10.1109","author":[{"given":"Xin","family":"Dong","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shichao","family":"Dong","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhou","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zenghui","family":"Sun","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihua","family":"Jing","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsong","family":"Lan","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02784"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"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","first-page":"335","article-title":"Audio chord recognition with recurrent neural networks","volume-title":"In ISMIR","author":"Boulanger-Lewandowski","year":"2013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31384-3"},{"key":"ref6","article-title":"Harsanyinet: Computing accurate shapley values in a single forward propagation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref8","article-title":"Mitigating hallucination in visual language models with visual supervision","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref11","article-title":"Halc: Object hallucination reduction via adaptive focal-contrast decoding","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"issue":"3","key":"ref12","first-page":"6","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 % chatgpt quality"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref14","article-title":"Discovering and explaining the representation bottleneck of dnns","author":"Deng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01316"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3119110"},{"key":"ref19","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s001820050125"},{"key":"ref21","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-2527-9_3"},{"key":"ref23","article-title":"The curious case of neural text degeneration","volume-title":"International Conference on Learning Representations","author":"Holtzman"},{"key":"ref24","author":"Honnibal","year":"2017","journal-title":"spacy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. (No Title)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref26","article-title":"Self-introspective decoding: Alleviating hallucinations for large vision-language models","author":"Huo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02644"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.687"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref35","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","author":"Liu","year":"2025","journal-title":"Llava-bench in the wild dataset"},{"key":"ref37","author":"Liu","year":"2023","journal-title":"Improved baselines with visual instruction tuning"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32689"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.30"},{"key":"ref41","article-title":"Look, compare, decide:Alleviating hallucination in large visionlanguage models via multi-view multi-path reasoning","author":"Qu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"A unified game-theoretic interpretation of adversarial robustness","volume":"4","author":"Ren","year":"2021","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Can we faithfully represent masked states to compute shapley values on a dnn?","author":"Ren","year":"2021","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01942"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref48","article-title":"The good, the bad, and the greedy: Evaluation of llms should not ignore non-determinism","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Aligning large multimodal models with factually augmented rlhf","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","first-page":"9269","article-title":"The many shapley values for model explanation","volume-title":"In International conference on machine learning","author":"Sundararajan"},{"key":"ref51","first-page":"9259","article-title":"The shapley taylor interaction index","volume-title":"In International conference on machine learning","author":"Sundararajan"},{"key":"ref52","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref53","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"An 11 m -free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Diagnosing the compositional knowledge of vision language models from a game-theoretic view","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"A unified approach to interpreting and boosting adversarial transferability","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00113"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00194"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.633"},{"key":"ref62","first-page":"arXiv","article-title":"Halle-switch: Controlling object hallucination in large vision language models","author":"Zhai","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17685"},{"key":"ref64","article-title":"Game-theoretic interactions of different orders","author":"Zhang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17299"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29655"},{"key":"ref67","article-title":"Look twice before you answer: Memory-space visual retracing for hallucination mitigation in multimodal large language models","author":"Zou","year":"2024","journal-title":"arXiv preprint"}],"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\/11445025.pdf?arnumber=11445025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:17Z","timestamp":1777613477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00244","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}