@inproceedings{shallouf-etal-2025-compuge,
title = "{C}omp{UGE}-Bench: Comparative Understanding and Generation Evaluation Benchmark for Comparative Question Answering",
author = "Shallouf, Ahmad and
Nikishina, Irina and
Biemann, Chris",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven and
Mather, Brodie and
Dras, Mark",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: System Demonstrations",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-demos.19/",
pages = "189--198",
abstract = "This paper presents CompUGE, a comprehensive benchmark designed to evaluate Comparative Question Answering (CompQA) systems. The benchmark is structured around four core tasks: Comparative Question Identification, Object and Aspect Identification, Stance Classification, and Answer Generation. It unifies multiple datasets and provides a robust evaluation platform to compare various models across these sub-tasks. We also create additional all-encompassing CompUGE datasets by filtering and merging the existing ones. The benchmark for comparative question answering sub-tasks is designed as a web application available on HuggingFace Spaces: https://huggingface.co/spaces/uhhlt/CompUGE-Bench"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shallouf-etal-2025-compuge">
<titleInfo>
<title>CompUGE-Bench: Comparative Understanding and Generation Evaluation Benchmark for Comparative Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Shallouf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Nikishina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</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: System Demonstrations</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>
<name type="personal">
<namePart type="given">Brodie</namePart>
<namePart type="family">Mather</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dras</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>This paper presents CompUGE, a comprehensive benchmark designed to evaluate Comparative Question Answering (CompQA) systems. The benchmark is structured around four core tasks: Comparative Question Identification, Object and Aspect Identification, Stance Classification, and Answer Generation. It unifies multiple datasets and provides a robust evaluation platform to compare various models across these sub-tasks. We also create additional all-encompassing CompUGE datasets by filtering and merging the existing ones. The benchmark for comparative question answering sub-tasks is designed as a web application available on HuggingFace Spaces: https://huggingface.co/spaces/uhhlt/CompUGE-Bench</abstract>
<identifier type="citekey">shallouf-etal-2025-compuge</identifier>
<location>
<url>https://aclanthology.org/2025.coling-demos.19/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>189</start>
<end>198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CompUGE-Bench: Comparative Understanding and Generation Evaluation Benchmark for Comparative Question Answering
%A Shallouf, Ahmad
%A Nikishina, Irina
%A Biemann, Chris
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%Y Mather, Brodie
%Y Dras, Mark
%S Proceedings of the 31st International Conference on Computational Linguistics: System Demonstrations
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F shallouf-etal-2025-compuge
%X This paper presents CompUGE, a comprehensive benchmark designed to evaluate Comparative Question Answering (CompQA) systems. The benchmark is structured around four core tasks: Comparative Question Identification, Object and Aspect Identification, Stance Classification, and Answer Generation. It unifies multiple datasets and provides a robust evaluation platform to compare various models across these sub-tasks. We also create additional all-encompassing CompUGE datasets by filtering and merging the existing ones. The benchmark for comparative question answering sub-tasks is designed as a web application available on HuggingFace Spaces: https://huggingface.co/spaces/uhhlt/CompUGE-Bench
%U https://aclanthology.org/2025.coling-demos.19/
%P 189-198
Markdown (Informal)
[CompUGE-Bench: Comparative Understanding and Generation Evaluation Benchmark for Comparative Question Answering](https://aclanthology.org/2025.coling-demos.19/) (Shallouf et al., COLING 2025)
ACL