A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test 文章

ArXiv CS.CL2026-05-28NEWSen作者: Camilo Chac\'on Sartori, Jos\'e H. Garc\'ia
查看原文 →
关系图谱

A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test · 相关技术

相关技术

multi-hop RAGLLM-as-a-Judgelarge language modelsRetrieval-Augmented Generation