The perils of politeness: how large language models may amplify medical misinformation

Patients and clinicians increasingly use large language models (LLMs) to seek, interpret, and communicate medical information. Roughly one in five adults turns to LLMs for health advice, and clinician interest in communication and research applications is rising 1 , 2 , 3 , 4 . Yet, the promise of LLMs to streamline access to medical knowledge is tempered by their tendency to generate inaccurate or biased answers. Models can fabricate plausible information (called hallucinations) or be manipulated to generate harmful or misleading content 5 , 6 , 7 , 8 . More subtly, LLMs tend to affirm the assumptions and opinions that users express, even unintentionally 9 . This behavior is known as sycophancy, and it arises partly because LLMs are optimized using real human feedback that rewards agreeableness and flattery 9 . While LLMs are resultingly more pleasant to interact with, sycophancy threatens to reinforce user biases and spread misinformation by persuasively restating faulty inputs as medical fact 9 , 10 , 11 .