@inproceedings{ventirozos-etal-2025-aspect,
title = "Aspect{--}Sentiment Quad Prediction with Distilled Large Language Models",
author = "Ventirozos, Filippos Karolos and
Appleby, Peter and
Shardlow, Matthew",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.152/",
pages = "1309--1319",
abstract = "Aspect-based sentiment analysis offers detailed insights by pinpointing specific product aspects in a text that are associated with sentiments. This study explores it through the prediction of quadruples, comprising aspect, category, opinion, and polarity. We evaluated in-context learning strategies using recently released distilled large language models, ranging from zero to full-dataset demonstrations. Our findings reveal that the performance of these models now positions them between the current state-of-the-art and significantly higher than their earlier generations. Additionally, we experimented with various chain-of-thought prompts, examining sequences such as aspect to category to sentiment in different orders. Our results indicate that the optimal sequence differs from previous assumptions. Additionally, we found that for quadruple prediction, few-shot demonstrations alone yield better performance than chain-of-thought prompting."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ventirozos-etal-2025-aspect">
<titleInfo>
<title>Aspect–Sentiment Quad Prediction with Distilled Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Filippos</namePart>
<namePart type="given">Karolos</namePart>
<namePart type="family">Ventirozos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Appleby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Aspect-based sentiment analysis offers detailed insights by pinpointing specific product aspects in a text that are associated with sentiments. This study explores it through the prediction of quadruples, comprising aspect, category, opinion, and polarity. We evaluated in-context learning strategies using recently released distilled large language models, ranging from zero to full-dataset demonstrations. Our findings reveal that the performance of these models now positions them between the current state-of-the-art and significantly higher than their earlier generations. Additionally, we experimented with various chain-of-thought prompts, examining sequences such as aspect to category to sentiment in different orders. Our results indicate that the optimal sequence differs from previous assumptions. Additionally, we found that for quadruple prediction, few-shot demonstrations alone yield better performance than chain-of-thought prompting.</abstract>
<identifier type="citekey">ventirozos-etal-2025-aspect</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.152/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>1309</start>
<end>1319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aspect–Sentiment Quad Prediction with Distilled Large Language Models
%A Ventirozos, Filippos Karolos
%A Appleby, Peter
%A Shardlow, Matthew
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F ventirozos-etal-2025-aspect
%X Aspect-based sentiment analysis offers detailed insights by pinpointing specific product aspects in a text that are associated with sentiments. This study explores it through the prediction of quadruples, comprising aspect, category, opinion, and polarity. We evaluated in-context learning strategies using recently released distilled large language models, ranging from zero to full-dataset demonstrations. Our findings reveal that the performance of these models now positions them between the current state-of-the-art and significantly higher than their earlier generations. Additionally, we experimented with various chain-of-thought prompts, examining sequences such as aspect to category to sentiment in different orders. Our results indicate that the optimal sequence differs from previous assumptions. Additionally, we found that for quadruple prediction, few-shot demonstrations alone yield better performance than chain-of-thought prompting.
%U https://aclanthology.org/2025.ranlp-1.152/
%P 1309-1319
Markdown (Informal)
[Aspect–Sentiment Quad Prediction with Distilled Large Language Models](https://aclanthology.org/2025.ranlp-1.152/) (Ventirozos et al., RANLP 2025)
ACL
- Filippos Karolos Ventirozos, Peter Appleby, and Matthew Shardlow. 2025. Aspect–Sentiment Quad Prediction with Distilled Large Language Models. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1309–1319, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.