2 papers
cs.LG2026
Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
Guoxi Zhang, Jiawei Chen, Tianzhuo Yang +4
As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategicall…
cs.CL2024
Listening to Patients: A Framework of Detecting and Mitigating Patient Misreport for Medical Dialogue Generation
Lang Qin, Yao Zhang, Hongru Liang +2
Medical Dialogue Systems aim to provide automated healthcare support through patient-agent conversations. Previous efforts typically regard patients as ideal users -- one who accur…