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)→
More from Research
- Sam Altman: OpenAI will hunt for room-temperature superconductors with 1000s of AI agents — Dr_Singularity · 2026-09-09
- Nature: Connectomics Reveals How a Cerebellum-Like Circuit Learns Sensory Prediction — burny_tech · 2026-09-09
- 14B open model on one RTX 4090 matches hosted frontier model on text-to-SQL; mnemiq open-sourced — ycombinator · 2026-09-09
- Prof. Tom Yeh's new hand-solvable exercises demystify the context window — ProfTomYeh · 2026-09-09
- New discrete-diffusion LLM speedup paper Uno called out for similarity to Orthrus — _akhaliq · 2026-09-09
- Why Matrix Multiplication Keeps Showing Up in Unrelated Math Fields — burny_tech · 2026-09-09