RTLC——研究、教学相长、批判：一种受费曼学习技巧启发的三阶段提示范式，无需微调即可提升 JudgeBench 上的 LLM 即法官准确率

RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning