Vision-language models (VLMs) are increasingly deployed in socially sensitive applications, yet their behavior with respect to disability remains underexplored. We study disability aware descriptions for person centric images, where models often transition from evidence grounded factual description to interpretation shift including introduction of unsupported inferences beyond observable visual evidence. To systematically analyze this phenomenon, we introduce a benchmark based on paired Neutral Prompts (NP) and Disability-Contextualised Prompts (DP) and evaluate 15 state-of-the-art open- and closed-source VLMs under a zero-shot setting across 9 disability categories. Our evaluation framework treats interpretive fidelity as core objective and combines standard text-based metrics capturing affective degradation through shifts in sentiment, social regard and response length with an LLM-as-judge protocol, validated by annotators with lived experience of disability. We find that introducing disability context consistently degrades interpretive fidelity, inducing interpretation shifts characterised by speculative inference, narrative elaboration, affective degradation and deficit oriented framing. These effects are further amplified along race and gender dimension. Finally, we demonstrate targeted prompting and preference fine-tuning effectively improves interpretive fidelity and reduces substantially interpretation shifts.
Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational Contexts
School of Computer Science and Technology, East China Normal University(东华师范大学计算机科学与技术学院);Shanghai Institute of Artificial Intelligence for Education, East China Normal University(东华师范大学教育人工智能研究所);Faculty of Education, East China Normal University(东华师范大学教育学院)
Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection
University of Notre Dame(圣母大学);IBM Research(IBM研究院);Boston Children’s Hospital(波士顿儿童医院);Harvard Medical School(哈佛医学院);Optum AI, UnitedHealth Group(Optum AI, 联合健康集团)
VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
Key Laboratory of AI Safety of CAS, Institute of Computing Technology (ICT)(中国科学院人工智能安全重点实验室,计算技术研究所);University of Chinese Academy of Sciences (UCAS)(中国科学院大学);Peking University(北京大学)
SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs
Universidade Federal de Mato Grosso (UFMT)(马托格罗索联邦大学);Universidade Federal de Goiás (UFG)(戈亚斯联邦大学);Advanced Knowledge Center for Immersive Technologies (AKCIT)(沉浸式技术高级知识中心)
Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models
Volkswagen Aktiengesellschaft(大众汽车股份有限公司);L3S Research Center(莱比锡大学汉诺威研究中心);Faculty of Information Technology(信息科技学院);MOIA GmbH(MOIA公司);Motor AI GmbH(Motor AI公司)
An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation
University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence (TeleAI)(人工智能研究所);China Telecom(中国电信);School of Artificial Intelligence, Optics and Electronics (iOPEN)(人工智能、光学与电子学院);Northwestern Polytechnical University(西北工业大学)
Representing visual classification as a linear combination of words
Dana-Farber Cancer Institute(丹娜法伯癌症研究院);Reedy High School(里迪高中);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);Brigham and Women’s Hospital(布莱根妇女医院)
What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning
Birla Institute of Technology and Science, Pilani(贝拉理工科学学院皮拉尼分校);University of California, Merced(加州大学默塞德分校)