2 papers
cs.LG2026
PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue
Chenxuan Li, Jiayi Wan, Xinrong Chen +3
Large language models (LLMs) have made substantial progress on medical question-answering, yet effective medical dialogue also requires learning to ask questions that uncover relev…
cs.CL2026
Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue
Chenxuan Li, Xinrong Chen, Luyan Zhang +5
Proactive medical dialogue requires an agent to decide what to ask from incomplete patient information. Existing information-seeking approaches commonly prioritize questions that m…