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

MAKE IMPACT

Lianmin Zheng , Wei-Lin Chiang , Ying Sheng , Siyuan Zhuang , Zhanghao Wu , Yonghao Zhuang , Lin Zi , Zhuohan Li , Dacheng Li , Eric P. Xing , Hao Zhang , Joseph E. Gonzalez , Ion Stoica · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2306.05685

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.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2306.05685

PDF

https://arxiv.org/pdf/2306.05685

OA Status

green

Cited By

419

Related Works

10

OpenAlex ID

https://openalex.org/W4380353763

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4380353763

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2306.05685

Digital Object Identifier

Title

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

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-06-09

Full publication date if available

Authors

Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Lin Zi, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica

List of authors in order

Landing page

https://arxiv.org/abs/2306.05685

Publisher landing page

PDF URL

https://arxiv.org/pdf/2306.05685

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2306.05685

Direct OA link when available

Concepts

Computer science, Chatbot, Set (abstract data type), Complement (music), Benchmark (surveying), Crowdsourcing, Data science, Artificial intelligence, World Wide Web, Programming language, Complementation, Chemistry, Phenotype, Geography, Biochemistry, Geodesy, Gene

Top concepts (fields/topics) attached by OpenAlex

Cited by

419

Total citation count in OpenAlex

Citations by year (recent)

2025: 182, 2024: 177, 2023: 59, 2022: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload