Gender-Neutral Rewriting in Italian: Models, Approaches, and Trade-offs
This addresses the challenge of creating gender-neutral text in grammatical-gender languages like Italian, which is an incremental improvement over existing methods.
The researchers tackled gender-neutral rewriting in Italian by systematically evaluating large language models, finding that open-weight LLMs outperformed existing dedicated models and their fine-tuned models achieved comparable performance with much smaller 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.