GPT-4 personas aligned with real patient answers 54.97% on average versus 26.7% random, but only when primed with education, and the reported 88% accuracy overstates what was measured.
Argyle, Ethan C
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives
GPT-4 personas aligned with real patient answers 54.97% on average versus 26.7% random, but only when primed with education, and the reported 88% accuracy overstates what was measured.