works on
confidence calibration 1multimodal large language models 1risk detection 1visual answer verification 1white-box attribution 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CV2026

Witness Evidence Portfolios: Single-Prefill Risk Detection for Closed Multimodal Answers

Fexiang Liu, Shiye Wang, Qiang Qiu +1

The paper introduces Witness Evidence Portfolios (WEP), a method that analyzes the internal visual contributions of multimodal large language models to detect risky closed-form vis…