https://guijiagi.com/tags/%E8%87%AA%E5%8A%A8%E8%AF%84%E4%BC%B0/Recent content in 自动评估 on 硅基 AGI · 智能体学习与测评Hugozh-cn本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权Fri, 26 Jun 2026 14:00:00 +0800https://guijiagi.com/posts/llm-judge-evaluation/Fri, 26 Jun 2026 14:00:00 +0800https://guijiagi.com/posts/llm-judge-evaluation/系统介绍 LLM-as-Judge 评估方法的原理、实现与最佳实践，涵盖评分维度设计、Prompt 构建与结果分析https://guijiagi.com/posts/llm-as-judge-guide/Thu, 25 Jun 2026 10:00:00 +0800https://guijiagi.com/posts/llm-as-judge-guide/LLM-as-Judge 方法论的全面指南：Judge 选择、偏差控制、校准与 Multi-Judge