Year: 2025
Type: conference-paper
Abstract: Increasing attention is being dedicated by the NLP community to gender-fair practices, including emerging forms of non-binary language.Given the shift to the prompting paradigm for multiple tasks, direct comparisons between prompted and fine-tuned models in this context are lacking.We aim to fill this gap by comparing prompt engineering and fine-tuning techniques for gender-fair rewriting in Italian.We do so by framing a rewriting task where Italian gender-marked translations from English gender-ambiguous sentences are adapted into a gender-neutral alternative using direct non-binary language.We augment existing datasets with gender-neutral translations and conduct experiments to determine the best architecture and approach to complete such task, by fine-tuning and prompting seq2seq encoder-decoder and autoregressive decoderonly models.We show that smaller seq2seq models can reach good performance when finetuned, even with relatively little data; when it comes to prompts, including task demonstrations is crucial, and we find that chat-tuned models reach the best results in a few-shot setting.We achieve promising results, especially in contexts of limited data and resources.
Institution: University of Bologna
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4412944385