Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency
Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge. Traditional white-box interpretability methods are inapplicable to closed-source architectures and passive metrics fail to isolate causal features. We introduce Counterfactual Semantic Saliency (CSS). This black-box, model-agnostic framework quantifies the importance of objects by measuring the semantic shift induced by their causal ablation from a s
Record details
Published: 13 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy
arXiv · 13 May 2026
GRACE: Gradient-aligned Reasoning Data Curation for Efficient Post-training
arXiv · 13 May 2026
Exact Linear Attention
arXiv · 13 May 2026
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
arXiv · 13 May 2026
Sustaining AI safety: Control-theoretic external impossibility, intrinsic necessity, and structural requirements
arXiv · 13 May 2026
STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
arXiv · 13 May 2026
How to cite this record
ethics.ai (13 May 2026), “Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency,” evidence record 4413, https://ethics.ai/record/4413 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.