Assessing Readability with LLMs: The Role of Reasoning and Few-Shot Prompting
A systematic benchmark of diverse open-source LLMs for multilingual readability assessment is conducted, focusing on the prediction of discrete readability levels required by educational frameworks, to establish the viability of out-of-the-box LLMs as robust, cross-lingual readability assessors.
Raphaël Thieffry, M. Martinc
· 0 citations