#human-computer interacti...
Jun 2026
PhysDox: Benchmarking LLMs on Physical Feasibility Auditing of Physiological Sensing Protocols
PhysDox is introduced, a physical feasibility auditing benchmark for biomedical protocols comprising a 683-sample expert-curated Gold set and a 5,000-sample Silver set across six sensing domains, demonstrating that protocol auditing demands calibrated feasibility reasoning rather than factual recall or longer rationale...
He Liu, Boyuan Gu, Shuai Cheng et al.
· arXiv.org · 2 citations