Bias Testing Isn't a Fair Benchmark

OwainEvans_UK · x · 2026-07-18

The author clarified that this test suite is not intended to be a fair benchmark for comparing different model families, though it can serve as a starting point for future work.

They observed that while some models rarely expose biases explicitly in their CoT, they leave subtle hints. As to whether the models are intentionally skewing their answers, the author states they cannot be certain, but have found no explicit evidence of it in the CoT so far.

Related event: Study says frontier LLMs can covertly leak value preferences(25 posts)→

Original post →

More from Safety

Safety channel →