{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:59:07Z","timestamp":1775627947497,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":[[2025,12,3]]},"DOI":"10.1109\/icmla66185.2025.00124","type":"proceedings-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:54:58Z","timestamp":1775591698000},"page":"842-847","source":"Crossref","is-referenced-by-count":0,"title":["Towards Reliable Reasoning in Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Chinh","family":"Hoang","sequence":"first","affiliation":[{"name":"University of Nebraska-Lincoln,Electrical and Computer Engineering,Lincoln,NE,USA"}]},{"given":"Youssef","family":"Nassef","sequence":"additional","affiliation":[{"name":"University of Nebraska-Lincoln,Electrical and Computer Engineering,Lincoln,NE,USA"}]},{"given":"Mohammad Rashedul","family":"Hasan","sequence":"additional","affiliation":[{"name":"University of Nebraska-Lincoln,Electrical and Computer Engineering,Lincoln,NE,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2024.01.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"ref4","article-title":"PaLM: Scaling Language Modeling with Pathways","author":"Chowdhery","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01316"},{"key":"ref6","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref8","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref10","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref13","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02064"},{"key":"ref16","volume-title":"Thinking, fast and slow","author":"Kahneman","year":"2011"},{"key":"ref17","article-title":"Procedural knowledge in pretraining drives reasoning in large language models","author":"Ruis","year":"2024"},{"key":"ref18","article-title":"Hello gpt-4o","year":"2024"},{"key":"ref19","article-title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","author":"Birhane","year":"2021"},{"key":"ref20","article-title":"A survey on bias and fairness in machine learning","volume":"54","author":"Mehrabi","year":"2021","journal-title":"ACM Comput. Surv"},{"key":"ref21","article-title":"Debiasing multimodal large language models","author":"Zhang","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1161"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00434"},{"key":"ref24","article-title":"spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing","author":"Honnibal","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1201.0490"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref27","article-title":"Cogvlm2: Visual language models for image and video understanding","author":"Hong","year":"2024"},{"key":"ref28","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref29","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref30","article-title":"mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration","author":"Ye","year":"2023"},{"key":"ref31","article-title":"Qwenvl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref33","article-title":"Phi-3-vision-128k-instruct","year":"2024"},{"key":"ref34","article-title":"Mmhal-bench dataset-based evaluation of object hallucination","author":"Cao","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_12"},{"key":"ref37","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2023"}],"event":{"name":"2025 International Conference on Machine Learning and Applications (ICMLA)","location":"Boca Raton, FL, USA","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Machine Learning and Applications (ICMLA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11471302\/11471304\/11471472.pdf?arnumber=11471472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:19:50Z","timestamp":1775625590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icmla66185.2025.00124","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}