2 results for "Tao, Linwei"
Showing 1–2 · 0.14 seconds · RSS
-
Preprint Full text
Confidence Calibration under Ambiguous Ground Truth
Confidence calibration assumes a unique ground-truth label per input, yet this assumption fails wherever annotators genuinely disagree. Post-hoc calibrators fitted on majority-voted labels, the standard single-label targets used in practice, can appear well-calibrated under conventional evaluation…
-
Preprint Full text
Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration
Large Vision-Language Models (LVLMs) exhibit impressive multimodal reasoning capabilities but remain highly susceptible to object hallucination, where models generate responses that are not factually aligned with the visual content. Recent works attribute this issue to an inherent bias of LVLMs…