2 papers
cs.AI2025
Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework
Yunpu Zhao, Rui Zhang, Junbin Xiao +4
Large Vision-Language Models (LVLMs) have shown significant capability in vision-language understanding. However, one critical issue that persists in these models is sycophancy, wh…
cs.CV2025
Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation
Yunpu Zhao, Rui Zhang, Junbin Xiao +5
Vision-language models (VLMs) excel in various multimodal tasks but frequently suffer from poor calibration, resulting in misalignment between their verbalized confidence and respo…