Gender-Neutral Rewriting in Italian: Models, Approaches, and Trade-offs
Abstract
State-of-the-art large language models are evaluated for gender-neutral rewriting in Italian, showing that open-weight models outperform existing solutions, and fine-tuned models achieve competitive results with reduced size.
Gender-neutral rewriting (GNR) aims to reformulate text to eliminate unnecessary gender specifications while preserving meaning, a particularly challenging task in grammatical-gender languages like Italian. In this work, we conduct the first systematic evaluation of state-of-the-art large language models (LLMs) for Italian GNR, introducing a two-dimensional framework that measures both neutrality and semantic fidelity to the input. We compare few-shot prompting across multiple LLMs, fine-tune selected models, and apply targeted cleaning to boost task relevance. Our findings show that open-weight LLMs outperform the only existing model dedicated to GNR in Italian, whereas our fine-tuned models match or exceed the best open-weight LLM's performance at a fraction of its size. Finally, we discuss the trade-off between optimizing the training data for neutrality and meaning preservation.
Models citing this paper 4
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper