compass-judger-reward-based-evaluation

【效率与协作】Build generalist judge models for evaluating LLM outputs using verifiable rewards and policy gradient training. Create a 7B model competitive with much larger judges through reward-guided optimization and critical thinking decomposition. Use when you need reliable automated evaluation of model outputs across diverse tasks.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准