{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:13Z","timestamp":1778051533450,"version":"3.51.4"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00596","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6163-6173","source":"Crossref","is-referenced-by-count":0,"title":["GHOST: Getting to the Bottom of Hallucinations with A Multi-round Consistency Benchmark"],"prefix":"10.1109","author":[{"given":"Vibashan","family":"VS","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadine","family":"Chang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jenny","family":"Schmalfuss","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishal M.","family":"Patel","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiding","family":"Yu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose M.","family":"Alvarez","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"claude 3 haiku: our fastest model yet","year":"2024"},{"key":"ref2","article-title":"Gpt-4: Gpt-4o ( \u201co\u201d for \"omni\")"},{"key":"ref3","article-title":"Llama-3"},{"key":"ref4","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref5","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2196\/59505"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.inlg-main.12"},{"key":"ref9","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024"},{"key":"ref10","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024"},{"key":"ref11","article-title":"Pali: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.178"},{"key":"ref13","article-title":"Mitigating hallucination in visual language models with visual supervision","author":"Chen","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref17","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref19","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00410"},{"key":"ref21","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01363"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.70675\/802872a7z8092z4556za1fdz2c7af45f0e72"},{"key":"ref24","article-title":"Ciem: Contrastive instruction evaluation method for better instruction tuning","volume-title":"NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following","author":"Hu"},{"key":"ref25","article-title":"Minicpm: Unveiling the potential of small language models with scalable training strategies","author":"Hu","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.573"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"ref29","first-page":"3680","article-title":"BECEL: Benchmark for consistency evaluation of language models","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Jang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680576"},{"key":"ref31","article-title":"Mantis: Interleaved multi-image instruction tuning","author":"Jiang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02571"},{"key":"ref33","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"Krishna","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.148"},{"key":"ref35","article-title":"Introducing idefics: An open reproduction of state-of-the-art visual language model","author":"Laurencon","year":"2023"},{"key":"ref36","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref37","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"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref39","article-title":"Vila: On pre-training for visual language models","author":"Lin","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1340"},{"key":"ref41","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2024"},{"key":"ref42","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref43","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref44","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.383"},{"key":"ref48","first-page":"88","article-title":"On the systematicity of probing contextualized word representations: The case of hypernymy in bert","volume-title":"Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics","author":"Ravichander"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref50","article-title":"Eagle: Exploring the design space for multimodal llms with mixture of encoders","author":"Shi","year":"2024"},{"key":"ref51","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024"},{"key":"ref52","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref53","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal llms","author":"Tong","year":"2024"},{"key":"ref54","article-title":"Amber: An llm-free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53302-0_3"},{"key":"ref56","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023"},{"key":"ref57","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1032"},{"key":"ref60","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2023"},{"key":"ref61","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning","author":"Zitkovich"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492374.pdf?arnumber=11492374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:16:41Z","timestamp":1778048201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00596","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}