2025
BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models
Zsolt T. Kardkov{\'a}cs, Lynda Djennane, Anna Field, Boualem Benatallah, Yacine Gaci, Fabio Casati +1
EMNLP 2025
Sentiment Analysis (SA) models harbor inherent social biases that can be harmful in real-world applications. These biases are identified by examining the output of SA models for sentences that only vary in the identity groups of the subjects.Constructing natural, linguistically rich, relevant, and d