Papers
arxiv:2608.23313

EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models

Published on Aug 24
Authors:
,

Abstract

EviSafe introduces an evidence-grounded framework and benchmark to evaluate whether vision-language models make safe decisions for correct multimodal reasons rather than relying on superficial refusal patterns.

Vision-language model safety benchmarks typically evaluate only final responses: whether a model refuses, warns, or complies. This outcome-level view cannot tell whether a model is safe for the right multimodal reason. Safelooking behavior may reflect keyword-triggered refusal, missed visual hazards, or over-refusal of benign-sensitive inputs. We introduce EviSafe, an evidence-grounded framework for VLM safety that jointly evaluates natural user-facing behavior, explicit grounding in textual and visual evidence, and behavioral sensitivity to counterfactual changes in safety-critical evidence. EviSafeBench instantiates the framework as a controlled benchmark with 1,181 gold image-text scenarios and 2,452 targeted counterfactual variants across eight safety domains and eight risk-source types. Each scenario includes a gold safety decision, evidence annotations, a safe-response policy, and counterfactual interventions. The three-probe protocol queries models with natural-response, evidencereporting, and counterfactual-response prompts, then scores them using an evidence-aware judge. Across eleven evaluated VLMs, natural severity accuracy ranges from 27.6% to 52.8%, relaxed diagnostic consistency from 6.1% to 29.3%, and unsafe-to-safe counterfactual transition success from 30.4% to 58.4%. These gaps show that the evaluated VLMs are not reliably safe for the right multimodal reason and motivate evaluation beyond refusal counts.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2608.23313
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2608.23313 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2608.23313 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2608.23313 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.