MIRAGE: The Illusion of Visual Understanding

TL;DR

This paper reveals that multimodal AI models can generate detailed reasoning and perform well without actual visual input, exposing vulnerabilities in current evaluation methods and proposing a new benchmark for fair assessment.

Contribution

The paper uncovers mirage reasoning in multimodal models, demonstrates their high performance without images, and introduces B-Clean for unbiased evaluation of visual-language understanding.

Findings

Models generate detailed image descriptions without images.

Models achieve high benchmark scores without visual input.

Explicit instructions to guess reduce model performance.

Abstract

Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language reasoning remain surprisingly poorly understood. We report three findings that challenge prevailing assumptions about how these systems process and integrate visual information. First, Frontier models readily generate detailed image descriptions and elaborate reasoning traces, including pathology-biased clinical findings, for images never provided; we term this phenomenon mirage reasoning. Second, without any image input, models also attain strikingly high scores across general and medical multimodal benchmarks, bringing into question their utility and design. In the most extreme case, our model achieved the top rank on a standard chest X-ray question-answering benchmark without access to any images. Third, when models were explicitly instructed to guess answers without image access, rather than being implicitly prompted to assume images were present, performance declined markedly. Explicit guessing appears to engage a more conservative response regime, in contrast to the mirage regime in which models behave as though images have been provided. These findings expose fundamental vulnerabilities in how visual-language models reason and are evaluated, pointing to an urgent need for private benchmarks that eliminate textual cues enabling non-visual inference, particularly in medical contexts where miscalibrated AI carries the greatest consequence. We introduce B-Clean as a principled solution for fair, vision-grounded evaluation of multimodal AI systems.