Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models.

arXiv:2609.20139v1 Announce Type: cross Abstract: Vision-language models (VLMs) are fragile under image corruption. We find that the wording of the question affects VLMs in two opposite ways. Verbose questions make VLMs substantially more robust---e.g., rephra