@inproceedings{attri-etal-2025-llms,
title = "{LLM}s as Architects and Critics for Multi-Source Opinion Summarization",
author = "Attri, Anuj and
Attri, Arnav and
Banerjee, Suman and
Patil, Amey and
Chelliah, Muthusamy and
Garera, Nikesh and
Bhattacharyya, Pushpak",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.5/",
pages = "69--101",
ISBN = "979-8-89176-303-6",
abstract = "Multi-source Opinion Summarization (M-OS) extends beyond traditional opinion summarization by incorporating additional sources of product metadata such as descriptions, key features, specifications, and ratings, alongside reviews. This integration results in comprehensive summaries that capture both subjective opinions and objective product attributes essential for informed decision-making. While Large Language Models (LLMs) have shown significant success in various Natural Language Processing (NLP) tasks, their potential in M-OS remains largely unexplored. Additionally, the lack of evaluation datasets for this task has impeded further advancements. To bridge this gap, we introduce M-OS-EVAL, a benchmark dataset for evaluating multi-source opinion summaries across seven key dimensions: fluency, coherence, relevance, faithfulness, aspect coverage, sentiment consistency, and specificity. Our results demonstrate that M-OS significantly enhances user engagement, as evidenced by a user study in which, on average, 87{\%} of participants preferred M-OS over opinion summaries. Our experiments demonstrate that factually enriched summaries enhance user engagement. Notably, M-OS-PROMPTS exhibit stronger alignment with human judgment, achieving an average Spearman correlation of {\ensuremath{\rho}} = 0.74, which surpasses the performance of previous methodologies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="attri-etal-2025-llms">
<titleInfo>
<title>LLMs as Architects and Critics for Multi-Source Opinion Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Attri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnav</namePart>
<namePart type="family">Attri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suman</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amey</namePart>
<namePart type="family">Patil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muthusamy</namePart>
<namePart type="family">Chelliah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikesh</namePart>
<namePart type="family">Garera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Multi-source Opinion Summarization (M-OS) extends beyond traditional opinion summarization by incorporating additional sources of product metadata such as descriptions, key features, specifications, and ratings, alongside reviews. This integration results in comprehensive summaries that capture both subjective opinions and objective product attributes essential for informed decision-making. While Large Language Models (LLMs) have shown significant success in various Natural Language Processing (NLP) tasks, their potential in M-OS remains largely unexplored. Additionally, the lack of evaluation datasets for this task has impeded further advancements. To bridge this gap, we introduce M-OS-EVAL, a benchmark dataset for evaluating multi-source opinion summaries across seven key dimensions: fluency, coherence, relevance, faithfulness, aspect coverage, sentiment consistency, and specificity. Our results demonstrate that M-OS significantly enhances user engagement, as evidenced by a user study in which, on average, 87% of participants preferred M-OS over opinion summaries. Our experiments demonstrate that factually enriched summaries enhance user engagement. Notably, M-OS-PROMPTS exhibit stronger alignment with human judgment, achieving an average Spearman correlation of \ensuremathρ = 0.74, which surpasses the performance of previous methodologies.</abstract>
<identifier type="citekey">attri-etal-2025-llms</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.5/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>69</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMs as Architects and Critics for Multi-Source Opinion Summarization
%A Attri, Anuj
%A Attri, Arnav
%A Banerjee, Suman
%A Patil, Amey
%A Chelliah, Muthusamy
%A Garera, Nikesh
%A Bhattacharyya, Pushpak
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F attri-etal-2025-llms
%X Multi-source Opinion Summarization (M-OS) extends beyond traditional opinion summarization by incorporating additional sources of product metadata such as descriptions, key features, specifications, and ratings, alongside reviews. This integration results in comprehensive summaries that capture both subjective opinions and objective product attributes essential for informed decision-making. While Large Language Models (LLMs) have shown significant success in various Natural Language Processing (NLP) tasks, their potential in M-OS remains largely unexplored. Additionally, the lack of evaluation datasets for this task has impeded further advancements. To bridge this gap, we introduce M-OS-EVAL, a benchmark dataset for evaluating multi-source opinion summaries across seven key dimensions: fluency, coherence, relevance, faithfulness, aspect coverage, sentiment consistency, and specificity. Our results demonstrate that M-OS significantly enhances user engagement, as evidenced by a user study in which, on average, 87% of participants preferred M-OS over opinion summaries. Our experiments demonstrate that factually enriched summaries enhance user engagement. Notably, M-OS-PROMPTS exhibit stronger alignment with human judgment, achieving an average Spearman correlation of \ensuremathρ = 0.74, which surpasses the performance of previous methodologies.
%U https://aclanthology.org/2025.findings-ijcnlp.5/
%P 69-101
Markdown (Informal)
[LLMs as Architects and Critics for Multi-Source Opinion Summarization](https://aclanthology.org/2025.findings-ijcnlp.5/) (Attri et al., Findings 2025)
ACL
- Anuj Attri, Arnav Attri, Suman Banerjee, Amey Patil, Muthusamy Chelliah, Nikesh Garera, and Pushpak Bhattacharyya. 2025. LLMs as Architects and Critics for Multi-Source Opinion Summarization. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 69–101, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.