MisgenderMender: A Community-Informed Approach to Interventions for Misgendering

TL;DR

This paper introduces MisgenderMender, a dataset and task for detecting and correcting misgendering in text, based on community insights, to improve automated interventions and reduce harm caused by misgendering.

Contribution

It presents the first community-informed dataset and task for misgendering detection and correction, along with baseline evaluations and insights for future NLP model development.

Findings

Existing NLP systems struggle with misgendering detection and correction.

The MisgenderMender dataset contains 3,790 annotated instances from social media.

Community insights highlight key challenges and desired solutions for interventions.

Abstract

Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Misgendering, the act of incorrectly addressing someone's gender, inflicts serious harm and is pervasive in everyday technologies, yet there is a notable lack of research to combat it. We are the first to address this lack of research into interventions for misgendering by conducting a survey of gender-diverse individuals in the US to understand perspectives about automated interventions for text-based misgendering. Based on survey insights on the prevalence of misgendering, desired solutions, and associated concerns, we introduce a misgendering interventions task and evaluation dataset, MisgenderMender. We define the task with two sub-tasks: (i) detecting misgendering, followed by (ii) correcting misgendering where misgendering is present in domains where editing is appropriate. MisgenderMender comprises 3790 instances of social media content and LLM-generations about non-cisgender public figures, annotated for the presence of misgendering, with additional annotations for correcting misgendering in LLM-generated text. Using this dataset, we set initial benchmarks by evaluating existing NLP systems and highlighting challenges for future models to address. We release the full dataset, code, and demo at https://tamannahossainkay.github.io/misgendermender/.