AI RESEARCH
Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation
arXiv CS.CV
•
ArXi:2605.27136v1 Announce Type: new Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) for reliable predictions and real-world deployment. However, most existing methods are adapted from the LLM literature and primarily focus on the language modality, leaving the contribution of visual information to LVLM uncertainty largely underexplored. In this paper, we investigate how LVLMs process visual information and whether this process can be used to improve uncertainty estimation.