Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities on Visual-Question-Answering (VQA) benchmarks. However, their robustness against textual misinformation remains under-explored. While existing research has studied the effect of misinformation in text-only domains, it is not clear how VLMs arbitrate between contradictory information from different modalities. To bridge the gap, we first propose the CONTEXT-VQA (i.e., Conflicting Text) dataset, consisting of image-question pairs together with systematically generated persuasive prompts that deliberately conflict with visual evidence. Then, a thorough evaluation framework is designed and executed to benchmark the susceptibility of various models to these conflicting multimodal inputs. Comprehensive experiments over 11 state-of-the-art VLMs reveal that these models are indeed vulnerable to misleading textual prompts, often overriding clear visual evidence in favor of the conflicting text, and show an average performance drop of over 48.2% after only one round of persuasive conversation. Our findings highlight a critical limitation in current VLMs and underscore the need for improved robustness against textual manipulation.

Key Contributions

• CONTEXT-VQA dataset: image-question pairs paired with systematically generated persuasive prompts that deliberately conflict with visual evidence
• Evaluation framework benchmarking the susceptibility of 11 state-of-the-art VLMs to conflicting multimodal inputs
• Empirical finding that VLMs frequently override clear visual evidence in favor of misleading textual prompts, with an average accuracy drop of 48.2% after a single persuasive exchange

🛡️ Threat Analysis

Details

Similar Papers