Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts
Chenxiao Fan, Chongming Gao, Gangyi Zhang +8
Reinforcement learning with verifiable rewards (RLVR) trains reasoning models to produce correct answers, but does not ensure that their stated confidence is calibrated. The result…
cs.LG2025
Fine-grained List-wise Alignment for Generative Medication Recommendation
Chenxiao Fan, Chongming Gao, Wentao Shi +3
Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, existing systems rely on point-wise p…