In a four-task benchmark, GPT-4o, Llama3.1-70B, and Gemma2-2B outperform traditional text simplification systems on most automatic metrics, and GPT-4o is preferred over human-written references in a small human study.
Paragraph-level sim- plification of medical texts
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
-
Redefining Simplicity: Benchmarking Large Language Models from Lexical to Document Simplification
In a four-task benchmark, GPT-4o, Llama3.1-70B, and Gemma2-2B outperform traditional text simplification systems on most automatic metrics, and GPT-4o is preferred over human-written references in a small human study.