From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs

TL;DR

This paper introduces a method to reduce gender bias in large language models by fine-tuning them with a dataset of gender-inclusive language, leading to less stereotypical outputs.

Contribution

It develops a novel gender-inclusive fine-tuning dataset and demonstrates its effectiveness in reducing gender stereotypes in multiple LLMs.

Findings

Reduced gender-stereotyping tendencies in models after fine-tuning

Compiled a catalogue of 692 gender-exclusive and neutral terms

Provides a practical approach for gender inclusivity in NLP

Abstract

Gender bias is not only prevalent in Large Language Models (LLMs) and their training data, but also firmly ingrained into the structural aspects of language itself. Therefore, adapting linguistic structures within LLM training data to promote gender-inclusivity can make gender representations within the model more inclusive. The focus of our work are gender-exclusive affixes in English, such as in 'show-girl' or 'man-cave', which can perpetuate gender stereotypes and binary conceptions of gender. We use an LLM training dataset to compile a catalogue of 692 gender-exclusive terms along with gender-neutral variants and from this, develop a gender-inclusive fine-tuning dataset, the 'Tiny Heap'. Fine-tuning three different LLMs with this dataset, we observe an overall reduction in gender-stereotyping tendencies across the models. Our approach provides a practical method for enhancing gender inclusivity in LLM training data and contributes to incorporating queer-feminist linguistic activism in bias mitigation research in NLP.