Amplifying Trans and Nonbinary Voices: A Community-Centred Harm Taxonomy for LLMs

Warning: some of the example prompts given in this paper are offensive including slurs. These are intended to illustrate potential harms. We explore large language model (LLM) responses that may negatively impact the transgender and nonbinary (TGNB) community and introduce the Transing Transformers Toolkit, T 3 , which provides resources for identifying such harmful response behaviors. The heart of T 3 is a community-centred taxonomy of harms, developed in collaboration with the TGNB community, which we complement with, amongst other guidance, suggested heuristics for evaluation. To develop the taxonomy, we adopted a multi-method approach that included surveys and focus groups with community experts. The contribution highlights the importance of community-centred approaches in mitigating harm, and outlines pathways for LLM developers to improve how their models handle TGNB-related topics. * Work conducted as a student researcher at Google Research.