SCOPE: Selective Conformal Optimized Pairwise LLM Judging
SCOPE: 选择性保形优化的成对LLM评判
机构 * Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada(达勒豪西大学计算机科学学院) ; Department of Computer Science, Emory University, Atlanta, GA, USA(埃默里大学计算机科学系)
专题命中 评测与基准 :LLM(title,title_cn);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI
AI总结 提出SCOPE框架,通过校准接受阈值控制非弃权判断的错误率,并引入双向偏好熵(BPE)提供无偏不确定性信号,实现可靠且高覆盖率的LLM成对评估。
Comments Accepted at ICML 2026. 23 pages (9 main plus appendix), 7 figures, 11 tables