Enhancing Digital Governance Through AI Text Revision: A Comparative Evaluation Using Controlled Error Injection
This study presents a comparative evaluation of 36 Large Language Model (LLM) configurations for automating Plain Language revision in digital public service. We introduce a Controlled Error Injection methodology, in which an auxiliary agent deliberately corrupts well-formed texts while preserving their factual content...
Emerson de Lima Assunção, Giovanna Machado Flores, Benito Toniolo Marino et al.
· Zenodo (CERN European Organi... · 0 citations