Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context

TL;DR

This study investigates how large language models process gender-inclusive language in coreference tasks, revealing biases that vary across languages and highlighting the importance of understanding LLMs' interpretative behaviors.

Contribution

It adapts psycholinguistic methods to analyze LLMs' handling of gender-inclusive language in English and German, uncovering biases and language-specific differences.

Findings

English LLMs generally maintain antecedent gender but show masculine bias.

German LLMs exhibit stronger bias, overriding neutralization strategies.

Biases vary significantly between English and German language models.

Abstract

Gender-inclusive language is often used with the aim of ensuring that all individuals, regardless of gender, can be associated with certain concepts. While psycholinguistic studies have examined its effects in relation to human cognition, it remains unclear how Large Language Models (LLMs) process gender-inclusive language. Given that commercial LLMs are gaining an increasingly strong foothold in everyday applications, it is crucial to examine whether LLMs in fact interpret gender-inclusive language neutrally, because the language they generate has the potential to influence the language of their users. This study examines whether LLM-generated coreferent terms align with a given gender expression or reflect model biases. Adapting psycholinguistic methods from French to English and German, we find that in English, LLMs generally maintain the antecedent's gender but exhibit underlying masculine bias. In German, this bias is much stronger, overriding all tested gender-neutralization strategies.