How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns
This addresses a social and linguistic challenge for non-binary inclusion and language model usability, but it is incremental as it builds on existing psycholinguistic findings.
The paper tackled the problem of language models' difficulty with gender-neutral pronouns, showing that they cause higher perplexity, more dispersed attention patterns, and worse downstream performance in Danish, English, and Swedish.
Gender-neutral pronouns have recently been introduced in many languages to a) include non-binary people and b) as a generic singular. Recent results from psycholinguistics suggest that gender-neutral pronouns (in Swedish) are not associated with human processing difficulties. This, we show, is in sharp contrast with automated processing. We show that gender-neutral pronouns in Danish, English, and Swedish are associated with higher perplexity, more dispersed attention patterns, and worse downstream performance. We argue that such conservativity in language models may limit widespread adoption of gender-neutral pronouns and must therefore be resolved.