Human-written plain language summaries led to significantly better reader comprehension than LLM-generated ones, despite similar subjective ratings, and most automated metrics did not predict comprehension.
Clearly communicating research results across the clinical trials continuum (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Are LLM-generated plain language summaries truly understandable? A large-scale crowdsourced evaluation
Human-written plain language summaries led to significantly better reader comprehension than LLM-generated ones, despite similar subjective ratings, and most automated metrics did not predict comprehension.