arXiv · NLP· Harine Choi (Texas A&M Transportation Institute, Texas A&M University System), Chenchen Kuai (Zachry Department of Civil and Environmental Engineering, Texas A&M University), Zihao Li (Department of Civil, Construction and Environmental Engineering, Marquette University), Jiwan Jiang (Zachry Department of Civil and Environmental Engineering, Texas A&M University), Yunlong Zhang (Zachry Department of Civil and Environmental Engineering, Texas A&M University), Zhiwen Fan (Department of Electrical and Computer Engineering, Texas A&M University), Zhengzhong Tu (Department of Computer Science and Engineering, Texas A&M University), Yang Zhou (Zachry Department of Civil and Environmental Engineering, Texas A&M University)·· 4 小时前AI 评分22
从自我信心到统计准确性：使用直接和 LLM 辅助审计扩展人工参与评估
From Self-Confidence to Statistical Accuracy: Scaling Human-in-the-Loop Evaluation with Direct and LLM-Assisted Auditing
AI 导读
研究者提出统计框架，利用未校准的 LLM 自信心实现分层审计。 该框架包含直接审计与 LLM 裁判辅助两种路径，通过 MMLU-Pro 等基准验证了其在极度不平衡分布下的有效性。 该研究明确了自动化评估方法在统计与经济效率方面的应用边界。
来源：arXiv · NLP · arxiv.org