Empirical AI Papers: Reporting LLM Bias Without Human Baselines

JeremyNguyenPhD · x · 2026-07-04

The author points out a current trend in empirical AI papers: they report on LLM biases without mentioning that human biases in the same areas typically test higher, yet the titles still sensationalize the findings as "shocking AI bias." This serves as a critique of the methodological choices and narrative biases in LLM bias evaluations.

Original post →

More from Research

Research channel →