Privileged Counterfactual Question Credit (PCQC), which uses privileged patient information during training to learn from questions never asked, is introduced, which achieves 63.10% mean diagnostic accuracy, outperforming GRPO and ATPO by 4.38 and 4.21 percentage points, respectively.
Chen-Xuan Li, Jia-Yi Wan, Xin-Rong Chen et al.· 0 citations
Proactive medical dialogue requires an agent to decide what to ask from incomplete patient information. Existing information-seeking approaches commonly prioritize questions that most reduce diagnostic uncertainty, but this criterion overlooks an important property of medical diagnosis: different diagnostic errors can...
Chen-Xuan Li, Xin-Rong Chen, Lu-Ya Zhang et al.· 0 citations
PASK (Parser-Aware Structural KV Persistence), which turns parser-derived structure into layer-group-specific KV persistence decisions by using task-error sensitivity to set minimum protection floors and attention-output distortion to allocate residual KV capacity.
Lin Wu, Xin-Rong Chen· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.