Gender Bias in Emotion Recognition by Large Language Models
This addresses fairness issues in LLMs for emotion recognition, which is incremental as it builds on existing bias research in AI.
The study investigated gender bias in large language models (LLMs) when recognizing emotions from descriptions, finding that meaningful bias reduction requires training-based interventions rather than prompt-based methods.
The rapid advancement of large language models (LLMs) and their growing integration into daily life underscore the importance of evaluating and ensuring their fairness. In this work, we examine fairness within the domain of emotional theory of mind, investigating whether LLMs exhibit gender biases when presented with a description of a person and their environment and asked, ''How does this person feel?''. Furthermore, we propose and evaluate several debiasing strategies, demonstrating that achieving meaningful reductions in bias requires training based interventions rather than relying solely on inference-time prompt-based approaches such as prompt engineering, etc.