{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:12:34Z","timestamp":1778530354233,"version":"3.51.4"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0118201"],"award-info":[{"award-number":["2022ZD0118201"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037"],"award-info":[{"award-number":["U21B2037"]}],"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":["U22B2051"],"award-info":[{"award-number":["U22B2051"]}],"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":["62072389"],"award-info":[{"award-number":["62072389"]}],"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":["62302411"],"award-info":[{"award-number":["62302411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M732948"],"award-info":[{"award-number":["2023M732948"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2022J06001"],"award-info":[{"award-number":["2022J06001"]}]},{"name":"CCF-NetEase ThunderFire Innovation Research Funding","award":["CCF-Netease 202301"],"award-info":[{"award-number":["CCF-Netease 202301"]}]},{"name":"Zhongguancun Academy","award":["20240103"],"award-info":[{"award-number":["20240103"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tpami.2026.3656175","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:54:47Z","timestamp":1770152087000},"page":"6332-6346","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating and Mitigating Relationship Hallucinations in Large Vision-Language Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8633-758X","authenticated-orcid":false,"given":"Mingrui","family":"Wu","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3717-1255","authenticated-orcid":false,"given":"Jiale","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-6308","authenticated-orcid":false,"given":"Jiayi","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Hao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref2","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","first-page":"19 730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref6","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01749"},{"key":"ref10","article-title":"Mitigating hallucination in visual language models with visual supervision","author":"Chen","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3571946"},{"key":"ref13","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref14","article-title":"InternLM: A multilingual language model with progressively enhanced capabilities","author":"Team","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref16","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref17","first-page":"29 615","article-title":"Cheap and quick: Efficient vision-language instruction tuning for large language models","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"36","author":"Luo"},{"key":"ref18","first-page":"26 273","article-title":"AR-1-to-3: Single image to consistent 3D object generation via next-view prediction","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Zhang","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00488"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3523675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3583795"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref23","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref24","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024"},{"key":"ref25","article-title":"MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Sepehri","year":"2025"},{"key":"ref26","first-page":"2024","article-title":"MathVista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref29","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","volume-title":"Proc. 39th Annu. Conf. Neural Inform. Process. Syst. Datasets Benchmarks Track","author":"Fu","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref32","article-title":"MM-Vet: Evaluating large multimodal models for integrated capabilities","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Yu","year":"2024"},{"key":"ref33","article-title":"Q-Bench: A benchmark for general-purpose foundation models on low-level vision","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Wu","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref36","article-title":"FaithScore: Evaluating hallucinations in large vision-language models","author":"Jing","year":"2023"},{"key":"ref37","article-title":"KNVQA: A benchmark for evaluation knowledge-based VQA","author":"Cheng","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00054"},{"key":"ref39","article-title":"Evaluation and analysis of hallucination in large vision-language models","author":"Wang","year":"2023"},{"key":"ref40","article-title":"An LLM-free multi-dimensional benchmark for MLLMs hallucination evaluation","author":"Wang","year":"2023"},{"key":"ref41","first-page":"6562","article-title":"MLLM-as-a-judge: Assessing multimodal LLM-as-a-judge with vision-language benchmark","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Chen","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01847"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.322"},{"key":"ref44","article-title":"Towards analyzing and mitigating sycophancy in large vision-language models","author":"Zhao","year":"2024"},{"key":"ref45","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1093\/oed\/1147809233"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01350"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53302-0_3"},{"key":"ref50","article-title":"CIEM: Contrastive instruction evaluation method for better instruction tuning","volume-title":"Proc. NeurIPS 2023 Workshop Instruct. Tuning Instruct. Follow.","author":"Hu","year":"2023"},{"key":"ref51","article-title":"HallE-switch: Controlling object hallucination in large vision language models","author":"Zhai","year":"2023"},{"key":"ref52","article-title":"Analyzing and mitigating object hallucination in large vision-language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhou","year":"2024"},{"key":"ref53","article-title":"Generalization and hallucination of large vision-language models through a camouflaged lens","author":"Tang","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/icme59968.2025.11209377"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref56","article-title":"Lyrics: Boosting fine-grained language-vision alignment and comprehension via semantic-aware visual objects","author":"Lu","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25385"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28422"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_8"},{"key":"ref66","article-title":"Seeing is believing: Mitigating hallucination in large vision-language models via CLIP-guided decoding","volume-title":"Proc. Int. Conf. Learn. Representations 2024 Workshop Reliable Responsible Found. Models","author":"Deng","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02784"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.414"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.398"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref75","article-title":"Ferret: Refer and ground anything anywhere at any granularity","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"You","year":"2023"},{"key":"ref76","first-page":"45 206","article-title":"ControLMLLM: Training-free visual prompt learning for multimodal large language models","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"37","author":"Wu","year":"2024"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref79","article-title":"QWEN2. 5-VL technical report","author":"Bai","year":"2025"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref83","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11512030\/11371674.pdf?arnumber=11371674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:46:35Z","timestamp":1778528795000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11371674\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":83,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3656175","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}