{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:55Z","timestamp":1777890175647,"version":"3.51.4"},"reference-count":45,"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":["62276017,62406033,U1636211,61672081"],"award-info":[{"award-number":["62276017,62406033,U1636211,61672081"]}],"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\/iccv51701.2025.00441","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4637-4646","source":"Crossref","is-referenced-by-count":0,"title":["SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Xianfu","family":"Cheng","sequence":"first","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyuan","family":"Guan","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianjie","family":"Wu","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Zhang","sequence":"additional","affiliation":[{"name":"M-A-P"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaheng","family":"Liu","sequence":"additional","affiliation":[{"name":"M-A-P"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuying","family":"Mai","sequence":"additional","affiliation":[{"name":"M-A-P"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhoufutu","family":"Wen","sequence":"additional","affiliation":[{"name":"M-A-P"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Jin","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baorui","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixiao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhong","family":"Lu","sequence":"additional","affiliation":[{"name":"M-A-P"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hangyuan","family":"Ji","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongliang","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Huang","sequence":"additional","affiliation":[{"name":"M-A-P"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhoujun","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","volume-title":"Llama 3 model card.","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.26615\/issn.2603-2821.2023_006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/int.22944"},{"key":"ref5","first-page":"8","article-title":"Xformparser: A simple and effective multimodal multilingual semi-structured form parser","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679618"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.941"},{"key":"ref8","first-page":"1","article-title":"Chinese simpleqa: A chinese factuality evaluation for large language models","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"3","article-title":"Chinese simpleqa: A chinese factuality evaluation for large language models","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"8","article-title":"Measuring massive multitask language understanding","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hendrycks","year":"2021"},{"key":"ref11","article-title":"Ceval: A multi-level multi-discipline chinese evaluation suite for foundation models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"4","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref14","first-page":"8","article-title":"Naturalbench: Evaluating vision-language models on natural adversarial samples","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"2","article-title":"From generation to judgment: Opportunities and challenges of 11 m-as-a-judge","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.671"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00803"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.602"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126274"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref22","first-page":"8","article-title":"Mmbench: Is your multi-modal model an all-around player?","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref25","first-page":"1","year":"2023","journal-title":"Gpt-4 technical report. PREPRINT"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref27","first-page":"8","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.732"},{"key":"ref29","first-page":"1","article-title":"A comprehensive survey of hallucination mitigation techniques in large language models","author":"Tonmoy","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"273877483","volume-title":"Measuring short-form factuality in large language models.","author":"Wei","year":"2024"},{"key":"ref31","volume-title":"Measuring short-form factuality in large language models.","author":"Wei","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.746"},{"key":"ref33","first-page":"8","article-title":"Mmra: A benchmark for multi-granularity multi-image relational association","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34739"},{"key":"ref35","first-page":"3","article-title":"Baichuan 2: Open large-scale language models","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","first-page":"8","article-title":"Evaluating and aligning codellms on human preference","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Execrepobench: Multi-level executable code completion evaluation","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"ref39","first-page":"3","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref41","first-page":"3","article-title":"Mmmu-pro: A more robust multidiscipline multimodal understanding benchmark","author":"Yue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"8","article-title":"Cmmmu: A chinese massive multidiscipline multimodal understanding benchmark","volume":"abs\/2401.11944","author":"Zhang","year":"2024","journal-title":"ArXiv"},{"key":"ref43","first-page":"1","article-title":"Siren\u2019s song in the ai ocean: a survey on hallucination in large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.149"},{"key":"ref45","first-page":"3","article-title":"Dynamath: A dynamic visual benchmark for evaluating mathematical reasoning robustness of vision 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\/11445806.pdf?arnumber=11445806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:43Z","timestamp":1777613563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00441","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}