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
Expected-Severity-Risk (ESR) is proposed, a consequence-aware question-supervision objective that values each candidate by its expected reduction in severity-aware terminal risk, and its results support moving proactive medical dialogue beyond uncertainty reduction toward consequence-aware evidence acquisition.
Chen-Xuan Li, Xin-Rong Chen, Lu-Ya Zhang et al.· 0 citations
Compared with text-based LLM, Dolphin improved emotional-semantic alignment and patient-education outcomes, supporting bimodal alignment as a strategy for reducing misalignment-driven communication failures.
Pei-Xing Wan, Zigeng Huang, Haoquan Huang et al.· i Medicina· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.