Research

From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language Models

Single source1 source7 Oct 2026

arXiv:2610.07514v1 Announce Type: new Abstract: A vision-language model may need to combine an image with a prompt to recognize a safety risk that neither reveals alone.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.07514

← Back to all developments · Signals are a development reported by more than one source. See the methodology.