Every number corrected for LLM judge bias—even the effect size

IanArawjo · x · 2026-09-09

Researcher Ian Arawjo shows that in his work, every reported number—including effect sizes—has been corrected for LLM judge bias, a serious methodological response to the known biases of LLM-as-a-judge evaluation.

Related event: Researcher Corrects LLM Judge Bias, Effect Sizes Included(2 posts)→

Original post →

More from Research

Research channel →