A step-level reward model trained on expert-designed synthetic clinical errors detects injected note errors with 98.8% accuracy and selects physician-preferred notes with 56.2% accuracy.
Assessment and Plan
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise
A step-level reward model trained on expert-designed synthetic clinical errors detects injected note errors with 98.8% accuracy and selects physician-preferred notes with 56.2% accuracy.