I'm Fully Who I Am - Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation

I'm Fully Who I Am - Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation

Explore a 15-minute conference talk that addresses the critical issue of measuring biases in open language generation, with a focus on centering transgender and non-binary voices. Delve into the research presented by authors Anaelia Ovalle, Palash Goyal, Jwala Dhamala, Zack Jaggers, Kai-Wei Chang, Aram Galstyan, Richard Zemel, and Rahul Gupta at the Association for Computing Machinery (ACM). Gain insights into the importance of inclusive representation in language models and the methodologies employed to identify and mitigate biases against transgender and non-binary individuals in AI-generated content.