Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

TL;DR

This paper investigates using large language models like GPT-4 as scalable, explainable judges for evaluating chat assistants, demonstrating high agreement with human preferences through new benchmarks and addressing limitations of LLM-based evaluation.

Contribution

It introduces MT-bench and Chatbot Arena benchmarks to validate LLMs as judges, showing they can reliably match human preferences and complement traditional evaluation methods.

Findings

GPT-4 matches human preferences with over 80% agreement.

LLM judges effectively evaluate open-ended questions and model variants.

Proposed solutions mitigate biases and limitations of LLM-based evaluation.

Abstract

Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions. We examine the usage and limitations of LLM-as-a-judge, including position, verbosity, and self-enhancement biases, as well as limited reasoning ability, and propose solutions to mitigate some of them. We then verify the agreement between LLM judges and human preferences by introducing two benchmarks: MT-bench, a multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our results reveal that strong LLM judges like GPT-4 can match both controlled and crowdsourced human preferences well, achieving over 80% agreement, the same level of agreement between humans. Hence, LLM-as-a-judge is a scalable and explainable way to approximate human preferences, which are otherwise very expensive to obtain. Additionally, we show our benchmark and traditional benchmarks complement each other by evaluating several variants of LLaMA and Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with human preferences are publicly available at https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.