LLMs generate more negative and harder-to-read clinical responses than physicians, but collaborative rewriting achieves highest semantic alignment, better readability, and patient preference without surpassing physicians on accuracy.
Assessing empathy in large language models with real-world physician-patient interactions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can "AI" Be a Doctor? A Study of Empathy, Readability, and Alignment in Clinical LLMs
LLMs generate more negative and harder-to-read clinical responses than physicians, but collaborative rewriting achieves highest semantic alignment, better readability, and patient preference without surpassing physicians on accuracy.