MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability
MedConceal, a benchmark with an interactive patient simulator for evaluating hidden-concern reasoning in medical dialogue, comprising 300 curated cases and 600 clinician-LLM interactions is presented, identifying hidden-concern reasoning under partial observability as a key unresolved challenge for medical dialogue systems.
Yikun Han, Joey Chan, Jingyuan Chen et al.
· arXiv.org · 1 citation