@inproceedings{yin-etal-2026-decentralized,
title = "Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models",
author = "Yin, Yanbin and
Zhou, Kun and
Wang, Zhen and
Zhang, Xiangdong and
Shao, Yifei and
Hao, Shibo and
Gu, Yi and
Liu, Jieyuan and
Singla, Somanshu and
Liu, Tianyang and
Xing, Eric P. and
Liu, Zhengzhong and
Jin, Haojian and
Hu, Zhiting",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1639/",
pages = "35453--35469",
ISBN = "979-8-89176-390-6",
abstract = "The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard practices nowadays face fundamental trade-offs: closed-ended question-based benchmarks (MMLU) struggle with saturation as newer models emerge, while crowd-sourced leaderboards (Chatbot Arena) rely on costly and slow human judges. Recently, automated methods (LLM-as-a-judge) shed light on the scalability, but risk bias by relying on one or a few ``authority'' models. To tackle these issues, we propose Decentralized Arena (), a fully automated framework leveraging collective intelligence from all LLMs to evaluate each other. It mitigates single-model judge bias by democratic, pairwise evaluation, and remains efficient at scale through two key components: (1) a coarse-to-fine ranking algorithm for fast incremental insertion of new models with sub-quadratic complexity, and (2) an automatic question selection strategy for the construction of new evaluation dimensions. Across extensive experiments across 66 LLMs, attains up to 97{\%} correlation with human judgements, while significantly reducing the cost."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2026-decentralized">
<titleInfo>
<title>Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanbin</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangdong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shibo</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Somanshu</namePart>
<namePart type="family">Singla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengzhong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haojian</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiting</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard practices nowadays face fundamental trade-offs: closed-ended question-based benchmarks (MMLU) struggle with saturation as newer models emerge, while crowd-sourced leaderboards (Chatbot Arena) rely on costly and slow human judges. Recently, automated methods (LLM-as-a-judge) shed light on the scalability, but risk bias by relying on one or a few “authority” models. To tackle these issues, we propose Decentralized Arena (), a fully automated framework leveraging collective intelligence from all LLMs to evaluate each other. It mitigates single-model judge bias by democratic, pairwise evaluation, and remains efficient at scale through two key components: (1) a coarse-to-fine ranking algorithm for fast incremental insertion of new models with sub-quadratic complexity, and (2) an automatic question selection strategy for the construction of new evaluation dimensions. Across extensive experiments across 66 LLMs, attains up to 97% correlation with human judgements, while significantly reducing the cost.</abstract>
<identifier type="citekey">yin-etal-2026-decentralized</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1639/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>35453</start>
<end>35469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models
%A Yin, Yanbin
%A Zhou, Kun
%A Wang, Zhen
%A Zhang, Xiangdong
%A Shao, Yifei
%A Hao, Shibo
%A Gu, Yi
%A Liu, Jieyuan
%A Singla, Somanshu
%A Liu, Tianyang
%A Xing, Eric P.
%A Liu, Zhengzhong
%A Jin, Haojian
%A Hu, Zhiting
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F yin-etal-2026-decentralized
%X The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard practices nowadays face fundamental trade-offs: closed-ended question-based benchmarks (MMLU) struggle with saturation as newer models emerge, while crowd-sourced leaderboards (Chatbot Arena) rely on costly and slow human judges. Recently, automated methods (LLM-as-a-judge) shed light on the scalability, but risk bias by relying on one or a few “authority” models. To tackle these issues, we propose Decentralized Arena (), a fully automated framework leveraging collective intelligence from all LLMs to evaluate each other. It mitigates single-model judge bias by democratic, pairwise evaluation, and remains efficient at scale through two key components: (1) a coarse-to-fine ranking algorithm for fast incremental insertion of new models with sub-quadratic complexity, and (2) an automatic question selection strategy for the construction of new evaluation dimensions. Across extensive experiments across 66 LLMs, attains up to 97% correlation with human judgements, while significantly reducing the cost.
%U https://aclanthology.org/2026.acl-long.1639/
%P 35453-35469
Markdown (Informal)
[Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models](https://aclanthology.org/2026.acl-long.1639/) (Yin et al., ACL 2026)
ACL
- Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, Haojian Jin, and Zhiting Hu. 2026. Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 35453–35469, San Diego, California, United States. Association for Computational Linguistics.