Parsa Ashrafi Fashi

PRISM-BENCH: Diagnosing Grounded and Faithful Multimodal Reasoning Beyond Final-Answer Accuracy

Final-answer accuracy reports whether a vision-language model was right, but not whether its answer was grounded in the image, whether its stated reasoning reflects that evidence, or what the answer cost to produce. Those are the properties that decide whether a system can be deployed. We present PRISM-BENCH, a benchma...