Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context
This addresses the problem of potential gender bias in LLMs for users and applications, as it is incremental by adapting existing psycholinguistic methods to new contexts.
The study investigated how Large Language Models (LLMs) process gender-inclusive language in coreference tasks, finding that in English, LLMs generally maintain the antecedent's gender but show underlying masculine bias, while in German, this bias is much stronger and overrides all tested gender-neutralization strategies.
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.