10 papers
Retrieval-Augmented Linguistic Calibration
Yi-Fan Yeh, Linwei Tao, Minjing Dong +4
Linguistic cues such as "I believe" and "probably" offer an intuitive interface for communicating confidence, yet a generalisable, principled calibration framework for linguistic c…
Confidence Calibration under Ambiguous Ground Truth
Linwei Tao, Haoyang Luo, Minjing Dong +1
Confidence calibration assumes a unique ground-truth label per input, yet this assumption fails wherever annotators genuinely disagree. Post-hoc calibrators fitted on majority-vote…
Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration
Younan Zhu, Linwei Tao, Minjing Dong +1
Large Vision-Language Models (LVLMs) exhibit impressive multimodal reasoning capabilities but remain highly susceptible to object hallucination, where models generate responses tha…
Can Large Language Models Express Uncertainty Like Human?
Linwei Tao, Yi-Fan Yeh, Bo Kai +6
Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhanc…
WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling
Xiaoyang Li, Linwei Tao, Haohui Lu +3
Graph Neural Networks (GNNs) have demonstrated strong predictive performance on relational data; however, their confidence estimates often misalign with actual predictive correctne…
Sample Margin-Aware Recalibration of Temperature Scaling
Haolan Guo, Linwei Tao, Haoyang Luo +2
Recent advances in deep learning have significantly improved predictive accuracy. However, modern neural networks remain systematically overconfident, posing risks for deployment i…