CrowSPairs

CrowS-Pairs, a challenge dataset for measuring the degree to which U.S. stereotypical biases present in the masked language models (MLMs).

Papers using CrowSPairs (5)

A Comprehensive Study of Implicit and Explicit Biases in Large Language Models2025Addressing Stereotypes in Large Language Models: A Critical Examination and Mitigation2025Open-DeBias: Toward Mitigating Open-Set Bias in Language Models2025STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions2024Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models2024