@inproceedings{liu-etal-2024-summequal,
title = "{S}umm{EQ}u{AL}: Summarization Evaluation via Question Answering using Large Language Models",
author = "Liu, Junyuan and
Shi, Zhengyan and
Lipani, Aldo",
editor = "Dalvi Mishra, Bhavana and
Durrett, Greg and
Jansen, Peter and
Lipkin, Ben and
Neves Ribeiro, Danilo and
Wong, Lionel and
Ye, Xi and
Zhao, Wenting",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Reasoning and Structured Explanations (@ACL 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlrse-1.5/",
pages = "46--55",
abstract = "Summarization is hard to evaluate due to its diverse and abstract nature. Although N-gram-based metrics like BLEU and ROUGE are prevalent, they often do not align well with human evaluations. While model-based alternatives such as BERTScore improve, they typically require extensive labelled data. The advent of Large Language Models (LLMs) presents a promising avenue for evaluation. To this end, we introduce SummEQuAL, a novel content-based framework using LLMs for unified, reproducible summarization evaluation. SummEQuAL evaluates summaries by comparing their content with the source document, employing a question-answering approach to gauge both recall and precision. To validate SummEQuAL{'}s effectiveness, we develop a dataset based on MultiWOZ. We conduct experiments on SummEval and our MultiWOZ-based dataset, showing that SummEQuAL largely improves the quality of summarization evaluation. Notably, SummEQuAL demonstrates a 19.7{\%} improvement over QuestEval in terms of sample-level Pearson correlation with human assessments of consistency on the SummEval dataset. Furthermore, it exceeds the performance of the BERTScore baseline by achieving a 17.3{\%} increase in Spearman correlation on our MultiWOZ-based dataset. Our study illuminates the potential of LLMs for a unified evaluation framework, setting a new paradigm for future summarization evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2024-summequal">
<titleInfo>
<title>SummEQuAL: Summarization Evaluation via Question Answering using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyan</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aldo</namePart>
<namePart type="family">Lipani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Reasoning and Structured Explanations (@ACL 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bhavana</namePart>
<namePart type="family">Dalvi Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Jansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Lipkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Neves Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lionel</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenting</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Summarization is hard to evaluate due to its diverse and abstract nature. Although N-gram-based metrics like BLEU and ROUGE are prevalent, they often do not align well with human evaluations. While model-based alternatives such as BERTScore improve, they typically require extensive labelled data. The advent of Large Language Models (LLMs) presents a promising avenue for evaluation. To this end, we introduce SummEQuAL, a novel content-based framework using LLMs for unified, reproducible summarization evaluation. SummEQuAL evaluates summaries by comparing their content with the source document, employing a question-answering approach to gauge both recall and precision. To validate SummEQuAL’s effectiveness, we develop a dataset based on MultiWOZ. We conduct experiments on SummEval and our MultiWOZ-based dataset, showing that SummEQuAL largely improves the quality of summarization evaluation. Notably, SummEQuAL demonstrates a 19.7% improvement over QuestEval in terms of sample-level Pearson correlation with human assessments of consistency on the SummEval dataset. Furthermore, it exceeds the performance of the BERTScore baseline by achieving a 17.3% increase in Spearman correlation on our MultiWOZ-based dataset. Our study illuminates the potential of LLMs for a unified evaluation framework, setting a new paradigm for future summarization evaluation.</abstract>
<identifier type="citekey">liu-etal-2024-summequal</identifier>
<location>
<url>https://aclanthology.org/2024.nlrse-1.5/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>46</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SummEQuAL: Summarization Evaluation via Question Answering using Large Language Models
%A Liu, Junyuan
%A Shi, Zhengyan
%A Lipani, Aldo
%Y Dalvi Mishra, Bhavana
%Y Durrett, Greg
%Y Jansen, Peter
%Y Lipkin, Ben
%Y Neves Ribeiro, Danilo
%Y Wong, Lionel
%Y Ye, Xi
%Y Zhao, Wenting
%S Proceedings of the 2nd Workshop on Natural Language Reasoning and Structured Explanations (@ACL 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F liu-etal-2024-summequal
%X Summarization is hard to evaluate due to its diverse and abstract nature. Although N-gram-based metrics like BLEU and ROUGE are prevalent, they often do not align well with human evaluations. While model-based alternatives such as BERTScore improve, they typically require extensive labelled data. The advent of Large Language Models (LLMs) presents a promising avenue for evaluation. To this end, we introduce SummEQuAL, a novel content-based framework using LLMs for unified, reproducible summarization evaluation. SummEQuAL evaluates summaries by comparing their content with the source document, employing a question-answering approach to gauge both recall and precision. To validate SummEQuAL’s effectiveness, we develop a dataset based on MultiWOZ. We conduct experiments on SummEval and our MultiWOZ-based dataset, showing that SummEQuAL largely improves the quality of summarization evaluation. Notably, SummEQuAL demonstrates a 19.7% improvement over QuestEval in terms of sample-level Pearson correlation with human assessments of consistency on the SummEval dataset. Furthermore, it exceeds the performance of the BERTScore baseline by achieving a 17.3% increase in Spearman correlation on our MultiWOZ-based dataset. Our study illuminates the potential of LLMs for a unified evaluation framework, setting a new paradigm for future summarization evaluation.
%U https://aclanthology.org/2024.nlrse-1.5/
%P 46-55
Markdown (Informal)
[SummEQuAL: Summarization Evaluation via Question Answering using Large Language Models](https://aclanthology.org/2024.nlrse-1.5/) (Liu et al., NLRSE 2024)
ACL