Chong Lyu

TRICON-FAIR: TRIPLET CONTRASTIVE LEARNING FOR MITIGATING SOCIAL BIAS IN PRE-TRAINED LANGUAGE MODELS

The increasing utilization of large language models raises significant concerns about the propagation of social biases, which may result in harmful and unfair outcomes. However, existing debiasing methods treat the biased and unbiased samples independently, thus ignoring their mutual relationship. T…