LLM-as-a-Judge: Building Automated Evaluation Pipelines for AI Applications
中文摘要
本文介绍了如何利用大语言模型作为评委，为AI应用构建自动化评估流水线，属于AI工程基础系列。
English Summary
This guide discusses using LLMs as judges to build automated evaluation pipelines for AI applications, part of an AI engineering fundamentals series.
Original Excerpt
AI Engineering Fundamentals AI Evaluation · Part 5 Continue reading on Medium »