Publications
They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse
A study on the ability of Large Language Models (LLMs) to interpret implicit content in real-life political discourse that reveals significant limitations in their pragmatic understanding.
“It’s a further exercise in futility”: implicit content detection and classification in Italian political discourse. A pilot study.
A study on Large Language Models' (LLMs) ability to process implicit meaning in political discourse evaluates nine multilingual models on two binary tasks: implicit content detection and classification. LLMs are prompted with 7 different prompting techniques.
Valutazione di tecniche di prompt engineering per la semplificazione dell'italiano burocratico e professionale
An expert evaluation study on the automatic text simplification capabilities of ChatGPT on Italian beaureaucratic texts.
Exploiting ChatGPT to simplify Italian bureaucratic and professional texts
A study on using ChatGPT to simplify complex administrative and legal Italian texts evaluates the model’s effectiveness in rephrasing long sentences and nominal clusters using zero-shot, few-shot, and Chain-of-Thought prompting.
