@inproceedings{jinji-etal-2026-maple,
title = "{MAPLE}: Multi-Aspect Panels of {LLM} Evaluators for Open-Ended Questions",
author = "Jinji, Michinori and
Atarashi, Kyohei and
Takeuchi, Koh and
Kashima, Hisashi",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1351/",
doi = "10.18653/v1/2026.findings-acl.1351",
pages = "27071--27088",
ISBN = "979-8-89176-395-1",
abstract = "LLM-as-a-Judge, which uses LLMs to evaluate responses to open-ended questions, has seen significant growth in recent years. It has been adopted as a scalable alternative to manual human evaluation, such as crowdsourcing, which is often time-consuming and costly. However, the discrepancy between LLM-generated evaluations and human evaluations remains a critical problem in this field. To bridge this gap, we propose Multi-Aspect Panels of LLM Evaluators (MAPLE), a framework that orchestrates evaluations across multiple criteria using multiple LLMs. MAPLE integrates criterion-wise pairwise evaluations from multiple LLMs by estimating the importance of criteria and the reliability of individual evaluators. We conduct experiments with both open-source and closed-source models. Our results demonstrate that MAPLE achieves superior alignment with human evaluations compared to baselines, highlighting the importance of employing multi-agent and multi-criteria evaluation strategies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jinji-etal-2026-maple">
<titleInfo>
<title>MAPLE: Multi-Aspect Panels of LLM Evaluators for Open-Ended Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michinori</namePart>
<namePart type="family">Jinji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyohei</namePart>
<namePart type="family">Atarashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koh</namePart>
<namePart type="family">Takeuchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hisashi</namePart>
<namePart type="family">Kashima</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>LLM-as-a-Judge, which uses LLMs to evaluate responses to open-ended questions, has seen significant growth in recent years. It has been adopted as a scalable alternative to manual human evaluation, such as crowdsourcing, which is often time-consuming and costly. However, the discrepancy between LLM-generated evaluations and human evaluations remains a critical problem in this field. To bridge this gap, we propose Multi-Aspect Panels of LLM Evaluators (MAPLE), a framework that orchestrates evaluations across multiple criteria using multiple LLMs. MAPLE integrates criterion-wise pairwise evaluations from multiple LLMs by estimating the importance of criteria and the reliability of individual evaluators. We conduct experiments with both open-source and closed-source models. Our results demonstrate that MAPLE achieves superior alignment with human evaluations compared to baselines, highlighting the importance of employing multi-agent and multi-criteria evaluation strategies.</abstract>
<identifier type="citekey">jinji-etal-2026-maple</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1351</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1351/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>27071</start>
<end>27088</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAPLE: Multi-Aspect Panels of LLM Evaluators for Open-Ended Questions
%A Jinji, Michinori
%A Atarashi, Kyohei
%A Takeuchi, Koh
%A Kashima, Hisashi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F jinji-etal-2026-maple
%X LLM-as-a-Judge, which uses LLMs to evaluate responses to open-ended questions, has seen significant growth in recent years. It has been adopted as a scalable alternative to manual human evaluation, such as crowdsourcing, which is often time-consuming and costly. However, the discrepancy between LLM-generated evaluations and human evaluations remains a critical problem in this field. To bridge this gap, we propose Multi-Aspect Panels of LLM Evaluators (MAPLE), a framework that orchestrates evaluations across multiple criteria using multiple LLMs. MAPLE integrates criterion-wise pairwise evaluations from multiple LLMs by estimating the importance of criteria and the reliability of individual evaluators. We conduct experiments with both open-source and closed-source models. Our results demonstrate that MAPLE achieves superior alignment with human evaluations compared to baselines, highlighting the importance of employing multi-agent and multi-criteria evaluation strategies.
%R 10.18653/v1/2026.findings-acl.1351
%U https://aclanthology.org/2026.findings-acl.1351/
%U https://doi.org/10.18653/v1/2026.findings-acl.1351
%P 27071-27088
Markdown (Informal)
[MAPLE: Multi-Aspect Panels of LLM Evaluators for Open-Ended Questions](https://aclanthology.org/2026.findings-acl.1351/) (Jinji et al., Findings 2026)
ACL