@inproceedings{li-etal-2025-dna,
title = "{D}n{A}-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation",
author = "Li, Minzhi and
Liu, Zhengyuan and
Deng, Shumin and
Joty, Shafiq and
Chen, Nancy and
Kan, Min-Yen",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.156/",
pages = "2277--2290",
abstract = "The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated text. Though LLMs serve as scalable and economical evaluators, how reliable these evaluators is still under-explored. Prior research efforts in the meta-evaluation of LLMs as judges limit the prompting of an LLM to a single use to obtain a final evaluation decision. They then compute the agreement between LLMs' outputs and human labels. This lacks interpretability in understanding the evaluation capability of LLMs. In light of this challenge, we propose DnA-Eval, which breaks down the evaluation process into decomposition and aggregation stages based on pedagogical practices. Our experiments show that it not only provides a more interpretable window for how well LLMs evaluate, but also leads to improvements up to 39.6{\%} for different LLMs on a variety of meta-evaluation benchmarks."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-dna">
<titleInfo>
<title>DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minzhi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shumin</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated text. Though LLMs serve as scalable and economical evaluators, how reliable these evaluators is still under-explored. Prior research efforts in the meta-evaluation of LLMs as judges limit the prompting of an LLM to a single use to obtain a final evaluation decision. They then compute the agreement between LLMs’ outputs and human labels. This lacks interpretability in understanding the evaluation capability of LLMs. In light of this challenge, we propose DnA-Eval, which breaks down the evaluation process into decomposition and aggregation stages based on pedagogical practices. Our experiments show that it not only provides a more interpretable window for how well LLMs evaluate, but also leads to improvements up to 39.6% for different LLMs on a variety of meta-evaluation benchmarks.</abstract>
<identifier type="citekey">li-etal-2025-dna</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.156/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>2277</start>
<end>2290</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation
%A Li, Minzhi
%A Liu, Zhengyuan
%A Deng, Shumin
%A Joty, Shafiq
%A Chen, Nancy
%A Kan, Min-Yen
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F li-etal-2025-dna
%X The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated text. Though LLMs serve as scalable and economical evaluators, how reliable these evaluators is still under-explored. Prior research efforts in the meta-evaluation of LLMs as judges limit the prompting of an LLM to a single use to obtain a final evaluation decision. They then compute the agreement between LLMs’ outputs and human labels. This lacks interpretability in understanding the evaluation capability of LLMs. In light of this challenge, we propose DnA-Eval, which breaks down the evaluation process into decomposition and aggregation stages based on pedagogical practices. Our experiments show that it not only provides a more interpretable window for how well LLMs evaluate, but also leads to improvements up to 39.6% for different LLMs on a variety of meta-evaluation benchmarks.
%U https://aclanthology.org/2025.coling-main.156/
%P 2277-2290
Markdown (Informal)
[DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation](https://aclanthology.org/2025.coling-main.156/) (Li et al., COLING 2025)
ACL