Papers
arxiv:2606.06890

Diagnosing Visual Ignorance in Vision-Language Models

Published on Jun 5
Authors:
,
,

Abstract

Vision-language models exhibit systematic reliance on language priors that weakly align with visual evidence, identified through internal analysis of semantic competition in language decoders and external evaluation using progressive visual degradation metrics across multiple benchmarks.

Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence. While this behavior is widely observed, its internal mechanisms and its impact on benchmark evaluation remain insufficiently understood. In this work, we study language-prior reliance from both mechanistic and behavioral perspectives. Internally, we combine counterfactual layer replacement with supervised layer-wise MLP probing to trace how ground-truth visual semantics and language-prior semantics compete across the language decoder. Our analysis reveals a multi-stage bottleneck: intermediate layers often fail to effectively retrieve visual information, while later layers can further suppress surviving visual signals in favor of text-space biases. Externally, we introduce a progressive visual decay metric based on multi-step Gaussian blurring, which identifies instances whose answers remain invariant even as visual content is increasingly destroyed. Across twelve visual question-answering benchmarks and three representative VLMs, we find that a substantial fraction of examples remain answerable under severe or total visual obfuscation, indicating that current benchmarks can inadvertently reward visual ignorance. These findings demonstrate that language-prior reliance is a systematic routing failure affecting both model internals and benchmark validity. Finally, we outline critical pathways for future research, highlighting the necessity of designing training distributions and evaluation protocols built on structurally isolated or counterfactual data to enforce genuine cross-modal grounding.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.06890
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/2606.06890 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/2606.06890 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/2606.06890 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.