2 papers
cs.AI2026
IDEA: An Interpretable and Editable Decision-Making Framework for LLMs via Verbal-to-Numeric Calibration
Yanji He, Yuxin Jiang, Yiwen Wu +3
Large Language Models are increasingly deployed for decision-making, yet their adoption in high-stakes domains remains limited by miscalibrated probabilities, unfaithful explanatio…
cs.CV2025
Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection
Mingyang Chen, Jiawei Du, Bo Huang +3
Existing core-set selection methods predominantly rely on heuristic scoring signals such as training dynamics or model uncertainty, lacking explicit modeling of data likelihood. Th…