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

ArXiv CS.CV2026-07-31PAPERen作者: Fexiang Liu, Shiye Wang, Qiang Qiu, Zheng Wang

详细信息

来源站点
ArXiv CS.CV
作者
Fexiang Liu, Shiye Wang, Qiang Qiu, Zheng Wang
文章类型
PAPER
语言
en
发布日期
2026-07-31

摘要

arXiv:2607.27667v1 Announce Type: new Abstract: Reliable deployment of multimodal large language models (MLLMs) requires deciding whether a confident visual answer should be trusted, reviewed, or routed to a stronger system. Confidence scores capture candidate margins, but not where the estimated signed visual readouts associated with those margins come from or how they are distributed. We study inference-time risk detection for closed visual answers using the same white-box prefill path that produces the answer. Witness Evidence Portfolios (WEP) first estimates, layer by layer, which visual contributions support or contradict the predicted candidate. It summarizes these contributions through two interpretable route families: question-related evidence provenance and signed evidence concentration. Nested grouped validation chooses the more reliable family and a sparse top-k route portfolio, which is fused with candidate confidence.

相关事件

暂无数据

相关公司查看全部 (4)

A
ATHCOMPANY
A
ANDINONPROFIT
A
AMI团队RESEARCH_INSTITUTE

相关人物

暂无数据