Balanced Accuracy: The Right Metric for Evaluating LLM Judges -- Explained through Youden's J statistic
平衡准确率:评估大语言模型判官的正确指标——通过Youden的J统计量解释
机构 * Meta Superintelligence Labs(Meta超智能实验室) ; Meta ; University of Cambridge(剑桥大学)
AI总结 本文通过Youden的J统计量证明平衡准确率是评估LLM判官的更优指标,通过分析和实验展示其在选择判官时提升分类器鲁棒性的效果。
Comments 10 pages, 5 figures
Journal ref In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track), pages 927-936, Rabat, Morocco, March 2026