@inproceedings{kamoda-etal-2025-quantifying,
title = "Quantifying the Influence of Evaluation Aspects on Long-Form Response Assessment",
author = "Kamoda, Go and
Asai, Akari and
Brassard, Ana and
Sakaguchi, Keisuke",
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.588/",
pages = "8787--8808",
abstract = "Evaluating the outputs of large language models (LLMs) on long-form generative tasks remains challenging. While fine-grained, aspect-wise evaluations provide valuable diagnostic information, they are difficult to design exhaustively, and each aspect`s contribution to the overall acceptability of an answer is unclear. In this study, we propose a method to compute an overall quality score as a weighted average of three key aspects: factuality, informative- ness, and formality. This approach achieves stronger correlations with human judgments compared to previous metrics. Our analysis identifies factuality as the most predictive aspect of overall quality. Additionally, we release a dataset of 1.2k long-form QA answers annotated with both absolute judgments and relative preferences in overall and aspect-wise schemes to aid future research in evaluation practices."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kamoda-etal-2025-quantifying">
<titleInfo>
<title>Quantifying the Influence of Evaluation Aspects on Long-Form Response Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Go</namePart>
<namePart type="family">Kamoda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akari</namePart>
<namePart type="family">Asai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Brassard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keisuke</namePart>
<namePart type="family">Sakaguchi</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>Evaluating the outputs of large language models (LLMs) on long-form generative tasks remains challenging. While fine-grained, aspect-wise evaluations provide valuable diagnostic information, they are difficult to design exhaustively, and each aspect‘s contribution to the overall acceptability of an answer is unclear. In this study, we propose a method to compute an overall quality score as a weighted average of three key aspects: factuality, informative- ness, and formality. This approach achieves stronger correlations with human judgments compared to previous metrics. Our analysis identifies factuality as the most predictive aspect of overall quality. Additionally, we release a dataset of 1.2k long-form QA answers annotated with both absolute judgments and relative preferences in overall and aspect-wise schemes to aid future research in evaluation practices.</abstract>
<identifier type="citekey">kamoda-etal-2025-quantifying</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.588/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8787</start>
<end>8808</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quantifying the Influence of Evaluation Aspects on Long-Form Response Assessment
%A Kamoda, Go
%A Asai, Akari
%A Brassard, Ana
%A Sakaguchi, Keisuke
%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 kamoda-etal-2025-quantifying
%X Evaluating the outputs of large language models (LLMs) on long-form generative tasks remains challenging. While fine-grained, aspect-wise evaluations provide valuable diagnostic information, they are difficult to design exhaustively, and each aspect‘s contribution to the overall acceptability of an answer is unclear. In this study, we propose a method to compute an overall quality score as a weighted average of three key aspects: factuality, informative- ness, and formality. This approach achieves stronger correlations with human judgments compared to previous metrics. Our analysis identifies factuality as the most predictive aspect of overall quality. Additionally, we release a dataset of 1.2k long-form QA answers annotated with both absolute judgments and relative preferences in overall and aspect-wise schemes to aid future research in evaluation practices.
%U https://aclanthology.org/2025.coling-main.588/
%P 8787-8808
Markdown (Informal)
[Quantifying the Influence of Evaluation Aspects on Long-Form Response Assessment](https://aclanthology.org/2025.coling-main.588/) (Kamoda et al., COLING 2025)
ACL