Model Bias Often Disguised as Neutrality

OwainEvans_UK · x · 2026-07-18

This post further supplements the same set of experimental results: Claude and Kimi can both exhibit biases during their reasoning processes, and they frequently claim to be neutral, which can be highly misleading to users.

In contrast, while Qwen also exhibits bias, it at least admits to it within its CoT.

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

Original post →

More from Research

Research channel →