@inproceedings{nikishina-etal-2025-compare,
title = "How to Compare Things Properly? A Study of Argument Relevance in Comparative Question Answering",
author = "Nikishina, Irina and
Anwar, Saba and
Dolgov, Nikolay and
Manina, Maria and
Ignatenko, Daria and
Shelmanov, Artem and
Biemann, Chris",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.765/",
doi = "10.18653/v1/2025.acl-long.765",
pages = "15702--15720",
ISBN = "979-8-89176-251-0",
abstract = "Comparative Question Answering (CQA) lies at the intersection of Question Answering, Argument Mining, and Summarization. It poses unique challenges due to the inherently subjective nature of many questions and the need to integrate diverse perspectives. Although the CQA task can be addressed using recently emerged instruction-following Large Language Models (LLMs), challenges such as hallucinations in their outputs and the lack of transparent argument provenance remain significant limitations.To address these challenges, we construct a manually curated dataset comprising arguments annotated with their relevance. These arguments are further used to answer comparative questions, enabling precise traceability and faithfulness. Furthermore, we define explicit criteria for an ``ideal'' comparison and introduce a benchmark for evaluating the outputs of various Retrieval-Augmented Generation (RAG) models with respect to argument relevance. All code and data are publicly released to support further research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nikishina-etal-2025-compare">
<titleInfo>
<title>How to Compare Things Properly? A Study of Argument Relevance in Comparative Question Answering</title>
</titleInfo>
<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">Saba</namePart>
<namePart type="family">Anwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolay</namePart>
<namePart type="family">Dolgov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Manina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daria</namePart>
<namePart type="family">Ignatenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</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>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Comparative Question Answering (CQA) lies at the intersection of Question Answering, Argument Mining, and Summarization. It poses unique challenges due to the inherently subjective nature of many questions and the need to integrate diverse perspectives. Although the CQA task can be addressed using recently emerged instruction-following Large Language Models (LLMs), challenges such as hallucinations in their outputs and the lack of transparent argument provenance remain significant limitations.To address these challenges, we construct a manually curated dataset comprising arguments annotated with their relevance. These arguments are further used to answer comparative questions, enabling precise traceability and faithfulness. Furthermore, we define explicit criteria for an “ideal” comparison and introduce a benchmark for evaluating the outputs of various Retrieval-Augmented Generation (RAG) models with respect to argument relevance. All code and data are publicly released to support further research.</abstract>
<identifier type="citekey">nikishina-etal-2025-compare</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.765</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.765/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>15702</start>
<end>15720</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to Compare Things Properly? A Study of Argument Relevance in Comparative Question Answering
%A Nikishina, Irina
%A Anwar, Saba
%A Dolgov, Nikolay
%A Manina, Maria
%A Ignatenko, Daria
%A Shelmanov, Artem
%A Biemann, Chris
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F nikishina-etal-2025-compare
%X Comparative Question Answering (CQA) lies at the intersection of Question Answering, Argument Mining, and Summarization. It poses unique challenges due to the inherently subjective nature of many questions and the need to integrate diverse perspectives. Although the CQA task can be addressed using recently emerged instruction-following Large Language Models (LLMs), challenges such as hallucinations in their outputs and the lack of transparent argument provenance remain significant limitations.To address these challenges, we construct a manually curated dataset comprising arguments annotated with their relevance. These arguments are further used to answer comparative questions, enabling precise traceability and faithfulness. Furthermore, we define explicit criteria for an “ideal” comparison and introduce a benchmark for evaluating the outputs of various Retrieval-Augmented Generation (RAG) models with respect to argument relevance. All code and data are publicly released to support further research.
%R 10.18653/v1/2025.acl-long.765
%U https://aclanthology.org/2025.acl-long.765/
%U https://doi.org/10.18653/v1/2025.acl-long.765
%P 15702-15720
Markdown (Informal)
[How to Compare Things Properly? A Study of Argument Relevance in Comparative Question Answering](https://aclanthology.org/2025.acl-long.765/) (Nikishina et al., ACL 2025)
ACL