Template-based reports outperformed GPT-4 on clinical reliability, coherence, and results presentation while GPT-4 was more concise, based on ratings from eight speech therapists and students, yielding eight design recommendations.
Ehud Reiter, Roma Robertson, and Liesl M
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
-
Automated Clinical Report Generation for Remote Cognitive Remediation: Comparing Knowledge-Engineered Templates and LLMs in Low-Resource Settings
Template-based reports outperformed GPT-4 on clinical reliability, coherence, and results presentation while GPT-4 was more concise, based on ratings from eight speech therapists and students, yielding eight design recommendations.