Anaelia Ovalle

Latest

• SHADES: Towards a multilingual assessment of stereotypes in large language models (2025, NAACL)
• The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models (2025, ACM FAccT)
• Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies (2024, NAACL Findings)
• “I’m fully who I am”: Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation (ACM FAccT, 2023)
• Queer In AI: A Case Study in Community-Led Participatory AI (ACM FAcct Best Paper Award, 2023)
• Bound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harms
• Should they? Mobile Biometrics and Technopolicy meet Queer Community Considerations
• Factoring the Matrix of Domination: A Critical Review and Reimagination of Intersectionality in AI Fairness