Assessing the effectiveness of ChatGPT-3.5 and ChatGPT-4o in simplifying Italian institutional texts

This research aims to describe the performance of ChatGPT-3.5 and ChatGPT-4o in the task of Automatic Text Simplification (ATS) in Italian institutional texts. The aim is to analyse the linguistic differences between the original texts compared to their simplified rewritings by ChatGPT, and the imp...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Mariachiara Pascucci, Claudia Gigliotti
Format:	Artigo
Jezik:	Alemão
Izdano:	PUBLIA – SLUB Open Publishing 2025-10-01
Serija:	AI-Linguistica
Teme:	Large Language Models ChatGPT bureaucratic and professional texts linguistic simplification human evaluation
Online dostop:	https://ai-ling.publia.org/ai_ling/article/view/18
Oznake:	Označite Brez oznak, prvi označite!