Saved in:
Bibliographic Details
Main Authors: Zhao, Ruochen, Zhang, Wenxuan, Chia, Yew Ken, Xu, Weiwen, Zhao, Deli, Bing, Lidong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.20267
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914966254125056
author Zhao, Ruochen
Zhang, Wenxuan
Chia, Yew Ken
Xu, Weiwen
Zhao, Deli
Bing, Lidong
author_facet Zhao, Ruochen
Zhang, Wenxuan
Chia, Yew Ken
Xu, Weiwen
Zhao, Deli
Bing, Lidong
contents As LLMs continuously evolve, there is an urgent need for a reliable evaluation method that delivers trustworthy results promptly. Currently, static benchmarks suffer from inflexibility and unreliability, leading users to prefer human voting platforms like Chatbot Arena. However, human evaluations require significant manual effort. To address this, we propose the Auto-Arena, an innovative framework that automates the entire evaluation process using LLM-powered agents. Firstly, an LLM examiner generates questions. Then, two LLM candidates engage in a multi-round peer battle based on individual questions, aiming at revealing their true performance differences. Finally, a committee of LLM judges collaboratively discusses and decides the winner, reducing bias and enhancing fairness. During the peer battles, we observe intriguing scenarios where the LLM candidates display competitive behaviors and even learn from the opponents. In our extensive experiments involving 15 recent LLMs, Auto-Arena shows a 92.14% correlation with human preferences, surpassing all previous expert-annotated benchmarks without any manual efforts. As a result, Auto-Arena offers a promising alternative to current human evaluation platforms for evaluating LLMs automatically.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20267
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions
Zhao, Ruochen
Zhang, Wenxuan
Chia, Yew Ken
Xu, Weiwen
Zhao, Deli
Bing, Lidong
Computation and Language
As LLMs continuously evolve, there is an urgent need for a reliable evaluation method that delivers trustworthy results promptly. Currently, static benchmarks suffer from inflexibility and unreliability, leading users to prefer human voting platforms like Chatbot Arena. However, human evaluations require significant manual effort. To address this, we propose the Auto-Arena, an innovative framework that automates the entire evaluation process using LLM-powered agents. Firstly, an LLM examiner generates questions. Then, two LLM candidates engage in a multi-round peer battle based on individual questions, aiming at revealing their true performance differences. Finally, a committee of LLM judges collaboratively discusses and decides the winner, reducing bias and enhancing fairness. During the peer battles, we observe intriguing scenarios where the LLM candidates display competitive behaviors and even learn from the opponents. In our extensive experiments involving 15 recent LLMs, Auto-Arena shows a 92.14% correlation with human preferences, surpassing all previous expert-annotated benchmarks without any manual efforts. As a result, Auto-Arena offers a promising alternative to current human evaluation platforms for evaluating LLMs automatically.
title Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions
topic Computation and Language
url https://arxiv.org/abs/2405.20267