arXiv cs.AI
· Papers
TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
arXiv:2608.13167v1 Announce Type: cross Abstract: When visual evidence is occluded or chaotic, models should abstain. In this paper, we show that Vision-Language Models (VLMs) can internally distinguish when abstention is required, but fail to express it anyway. We introduce TRAPSBench, a procedurally generated video b