arXiv cs.CL
· Papers
ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues
arXiv:2604.01925v2 Announce Type: replace Abstract: Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly. Existing benchmarks use name based proxies to detect implicit biases, which carry wea