MISGENDERED: Limits of Large Language Models in Understanding Pronouns

TL;DR

This paper evaluates large language models' ability to correctly use non-binary and neo-pronouns, revealing significant limitations and proposing a framework for assessment and improvement.

Contribution

It introduces MISGENDERED, a comprehensive evaluation framework for pronoun usage in language models, highlighting their poor performance and the need for better representation of non-binary pronouns.

Findings

Models perform poorly on neo-pronouns (avg 7.7%)

Models perform poorly on gender-neutral pronouns (avg 34.2%)

Few-shot prompts improve accuracy up to 64.7%

Abstract

Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Gender bias in language technologies has been widely studied, but research has mostly been restricted to a binary paradigm of gender. It is essential also to consider non-binary gender identities, as excluding them can cause further harm to an already marginalized group. In this paper, we comprehensively evaluate popular language models for their ability to correctly use English gender-neutral pronouns (e.g., singular they, them) and neo-pronouns (e.g., ze, xe, thon) that are used by individuals whose gender identity is not represented by binary pronouns. We introduce MISGENDERED, a framework for evaluating large language models' ability to correctly use preferred pronouns, consisting of (i) instances declaring an individual's pronoun, followed by a sentence with a missing pronoun, and (ii) an experimental setup for evaluating masked and auto-regressive language models using a unified method. When prompted out-of-the-box, language models perform poorly at correctly predicting neo-pronouns (averaging 7.7% accuracy) and gender-neutral pronouns (averaging 34.2% accuracy). This inability to generalize results from a lack of representation of non-binary pronouns in training data and memorized associations. Few-shot adaptation with explicit examples in the prompt improves performance for neo-pronouns, but only to 64.7% even with 20 shots. We release the full dataset, code, and demo at https://tamannahossainkay.github.io/misgendered/