composo-ai/llm-judge-criteria-ensembling

An Empirical Investigation of Practical LLM-as-a-Judge Improvement Techniques on RewardBench 2

5 best points · 0 comments · 1 Hacker News post · 11 GitHub stars · View on GitHub

Hacker News discussions

• Composo open-sources its LLM-as-Judge technique (83.6% on RewardBench 2) (5 points, 0 comments, by mlukewizard, 2026-04-02)