Remi Denton — accepted AI-conference papers

2025

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

Eddie L. Ungless, Sunipa Dev, Cynthia L. Bennett, Rebecca Gulotta, Jasmijn Bastings, Remi Denton

ACL 2025long

We explore large language model (LLM) responses that may negatively impact the transgender and nonbinary (TGNB) community and introduce the Transing Transformers Toolkit, T3, which provides resources for identifying such harmful response behaviors. The heart of T3 is a community-centred taxonomy of…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation

Akshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo, Shachi Dave, Rida Qadri +2

ACL 2024long

Recent studies have shown that Text-to-Image (T2I) model generations can reflect social stereotypes present in the real world. However, existing approaches for evaluating stereotypes have a noticeable lack of coverage of global identity groups and their associated stereotypes. To address this gap, w…

Cited by 19 Source ↗PDF ↗code ↗Scholar ↗