{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:03Z","timestamp":1778048463019,"version":"3.51.4"},"reference-count":49,"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\/wacv61042.2026.00145","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1428-1437","source":"Crossref","is-referenced-by-count":0,"title":["You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction"],"prefix":"10.1109","author":[{"given":"Logan","family":"Lawrence","sequence":"first","affiliation":[{"name":"University of Massachusetts,Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oindrila","family":"Saha","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Megan","family":"Wei","sequence":"additional","affiliation":[{"name":"Brown University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Sun","sequence":"additional","affiliation":[{"name":"Brown University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhransu","family":"Maji","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grant","family":"Van Horn","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","year":"2023","journal-title":"Gpt-4v(ision) system card"},{"key":"ref2","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref3","author":"Ahn","year":"2022","journal-title":"Do as i can, not as i say: Grounding language in robotic affordances"},{"key":"ref4","author":"Bai","year":"2025","journal-title":"Qwen2. 5-vl technical report"},{"key":"ref5","author":"Beurer-Kellner","year":"2024","journal-title":"Guiding llms the right way: Fast, non-invasive constrained generation"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref7","author":"Chen","year":"2025","journal-title":"xverify: Efficient answer verifier for reasoning model evaluations"},{"issue":"5","key":"ref8","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023","volume":"3","author":"Chiang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref10","author":"Dong","year":"2024","journal-title":"Xgrammar: Flexible and efficient structured generation engine for large language models"},{"key":"ref11","author":"Gerganov","year":"2023","journal-title":"llama.cpp"},{"key":"ref12","author":"Grattafiori","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref13","year":"2023","journal-title":"Guidance"},{"key":"ref14","author":"Hendrycks","year":"2020","journal-title":"Measuring massive multitask language understanding"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.356"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref18","author":"Li","year":"2023","journal-title":"Alpacaeval: An automatic evaluator of instruction-following models"},{"key":"ref19","author":"Liang","year":"2022","journal-title":"Holistic evaluation of language models"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650756"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.knowllm-1.10"},{"key":"ref25","author":"Maji","year":"2013","journal-title":"Fine-grained visual classification of aircraft"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.950"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref29","year":"2025","journal-title":"Openai o3 and o4-mini system card"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"ref31","author":"Robinson","year":"2023","journal-title":"Leveraging large language models for multiple choice question answering"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref33","first-page":"29971","article-title":"Whose opinions do language models reflect?","volume-title":"International Conference on Machine Learning","author":"Santurkar"},{"key":"ref34","author":"Srivastava","year":"2022","journal-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.91"},{"key":"ref36","author":"Tan","year":"2025","journal-title":"Vision llms are bad at hierarchical visual understanding, and llms are the bottleneck"},{"key":"ref37","year":"2024","journal-title":"Introducing qwen1.5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref40","author":"Wah","year":"2011","journal-title":"The caltech-ucsd birds-200-2011 dataset"},{"key":"ref41","author":"Wang","year":"2025","journal-title":"Slot: Structuring the output of large language models"},{"key":"ref42","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","author":"Wang"},{"key":"ref43","author":"Wang","year":"2024","journal-title":"Look at the text: Instruction-tuned language models are more robust multiple choice selectors than you think"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.441"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3018"},{"key":"ref46","author":"Willard","year":"2023","journal-title":"Efficient guided generation for large language models"},{"key":"ref47","author":"Yu","year":"2024","journal-title":"xfinder: Robust and pinpoint answer extraction for large language models"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref49","author":"Zhu","year":"2025","journal-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models"}],"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\/11492412.pdf?arnumber=11492412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:04:12Z","timestamp":1778047452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00145","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}