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.
More from Research
- Stanford Data-Centric AI Workshop reopens site, extends poster deadline — jure · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Ito: a browser that detects browsing intent and auto-organizes tabs into Flows — andrewkuznet · 2026-10-26
- Cornell study says brains process language as linear sequences, challenging Chomsky's hierarchy — anirbanbandyo · 2026-10-26
- Hi3D V1.0 open-sourced with 2M training assets and 90% slicing success rate — kimmonismus · 2026-10-26
- Ortet evaluates 34 open-weight models on 50 health tasks, finds general leaderboards insufficient — elmanmansimov · 2026-10-26