Showing cs.HCShow all
2 papers · 1 filter
cs.HC2026
BioDisclose: An Actionability-Aware Benchmark for Biomedical Safety under Adversarial Elicitation
Yinuo Zhu, He Liu, Boyuan Gu
Large language models (LLMs) increasingly support biomedical research, yet their behavior under adversarial requests for dual-use knowledge remains insufficiently characterized. We…
cs.HC2026
PhysDox: Benchmarking LLMs on Physical Feasibility Auditing of Physiological Sensing Protocols
He Liu, Boyuan Gu, Shuaiqi Cheng +3
Large language models (LLMs) increasingly assist in experimental design, yet fluent protocols often remain physically infeasible. We introduce PhysDox, a physical feasibility audit…