A Prompt Response to the Demand for Automatic Gender-Neutral Translation

Beatrice Savoldi, Andrea Piergentili, Dennis Fucci, Matteo Negri, Luisa Bentivogli
2/8/2024
cs.CL

No official code found. Best implementation: hlt-mt/fbk-NEUTR-evAL (4 stars, Apache-2.0, last commit 2025-10-31).

Abstract

Gender-neutral translation (GNT) that avoids biased and undue binary assumptions is a pivotal challenge for the creation of more inclusive translation technologies. Advancements for this task in Machine Translation (MT), however, are hindered by the lack of dedicated parallel data, which are necessary to adapt MT systems to satisfy neutral constraints. For such a scenario, large language models offer hitherto unforeseen possibilities, as they come with the distinct advantage of being versatile in various (sub)tasks when provided with explicit instructions. In this paper, we explore this potential to automate GNT by comparing MT with the popular GPT-4 model. Through extensive manual analyses, our study empirically reveals the inherent limitations of current MT systems in generating GNTs and provides valuable insights into the potential and challenges associated with prompting for neutrality.

View on arXivView PDF

Code Implementations(1)

hlt-mt/fbk-NEUTR-evALCommunity100%
Apache-2.0
41PythonOct 4, 202311 months agoApache-2.0

Similar Papers

Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTE

89% match1 repo2025

Gender-Neutral Machine Translation Strategies in Practice

88% match2025

Gender Bias in Machine Translation and The Era of Large Language Models

88% match2024

Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translations

87% match1 repo2025

An LLM-as-a-judge Approach for Scalable Gender-Neutral Translation Evaluation

86% match2025

Generating Gender Alternatives in Machine Translation

86% match2024

Cite this paper

@article{savoldi2024prompt,
  title  = {A Prompt Response to the Demand for Automatic Gender-Neutral Translation},
  author = {Beatrice Savoldi and Andrea Piergentili and Dennis Fucci and Matteo Negri and Luisa Bentivogli},
  year   = {2024},
  eprint = {2402.06041},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.06041v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.06041.svg)](https://codeofpaper.com/paper/2402.06041)

Discussion