{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T06:01:17Z","timestamp":1784786477861,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"\u201cXingliao Talents Program\u201d Science and Technology Innovation Team Project","award":["XLYC2404007"],"award-info":[{"award-number":["XLYC2404007"]}]},{"name":"Liaoning Provincial Applied Basic Research Program","award":["2025JH2\/101300053"],"award-info":[{"award-number":["2025JH2\/101300053"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3711096","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:43:54Z","timestamp":1783539834000},"page":"109309-109331","source":"Crossref","is-referenced-by-count":0,"title":["Beyond VQA Accuracy: A Cross-Regime Diagnostic Evaluation of Symbol Consistency in Multimodal Large Language Models"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8149-558X","authenticated-orcid":false,"given":"Chuanchen","family":"Wang","sequence":"first","affiliation":[{"name":"Shenyang Institute of Computing Technology","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruifeng","family":"Guo","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Xiu","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5484-286X","authenticated-orcid":false,"given":"Hongliang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"19730","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"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref5","volume-title":"InternVL2: Better Than the Best\u2014Expanding Performance Boundaries of Open-Source Multimodal Models With the Progressive Scaling Strategy","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref9","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv:2306.13394"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref15","article-title":"MM-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv:2308.02490"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3440756"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3808699"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2026.3672135"},{"key":"ref25","article-title":"OCRBench v2: An improved benchmark for evaluating large multimodal models on visual text localization and reasoning","author":"Fu","year":"2024","journal-title":"arXiv:2501.00321"},{"key":"ref26","article-title":"ReadBench: Measuring the dense text visual reading ability of vision-language models","author":"Clavi\u00e9","year":"2025","journal-title":"arXiv:2505.19091"},{"key":"ref27","article-title":"MME-VideoOCR: Evaluating OCR-based capabilities of multimodal LLMs in video scenarios","author":"Shi","year":"2025","journal-title":"arXiv:2505.21333"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.69882\/adba.ai.2026014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.69882\/adba.csai.2026011"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.69882\/adba.csai.2026013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.69882\/adba.csai.2026015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref35","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv:2402.00253"},{"key":"ref36","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref40","first-page":"1","article-title":"MathVista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11599554.pdf?arnumber=11599554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T05:08:04Z","timestamp":1784783284000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11599554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3711096","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}