Session: Is AI Sexist? Examining Gender Bias in Large Language Models
This presentation delves into gender bias in Transformer models that power Large Language Models (LLMs) like ChatGPT, discussing challenges in measuring bias impact and promoting equity in AI systems. We’ll analyze bias sources in natural language processing (NLP), emphasizing collaborative efforts to address gender bias. The talk aims to spark discussions on detecting bias and deploying fair language models. It stresses the importance of unbiased AI systems in countering inadvertent biases.
