@inproceedings{gargova-etal-2025-comparative,
title = "A Comparative Study of Hyperbole Detection Methods: From Rule-Based Approaches through Deep Learning Models to Large Language Models",
author = "Gargova, Silvia and
Grigorova, Nevena and
Mitkov, Ruslan",
editor = "Picazo-Izquierdo, Alicia and
Estevanell-Valladares, Ernesto Luis and
Mitkov, Ruslan and
Guillena, Rafael Mu{\~n}oz and
Cerd{\'a}, Ra{\'u}l Garc{\'i}a",
booktitle = "Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.r2lm-1.4/",
pages = "30--38",
abstract = "We address hyperbole detection as a binary classification task, comparing rule-based methods, fine-tuned transformers (BERT, RoBERTa), and large language models (LLMs) in zero-shot and few-shot prompting (Gemini, LLaMA). Fine-tuned transformers achieved the best overall performance, with RoBERTa attaining an F1-score of 0.82. Rule-based methods performed lower (F1 = 0.58) but remain effective in constrained linguistic contexts. LLMs showed mixed results: zero-shot performance was variable, while few-shot prompting notably improved outcomes, reaching F1-scores up to 0.79 without task-specific training data. We discuss the trade-offs between interpretability, computational cost, and data requirements across methods. Our results highlight the promise of LLMs in low-resource scenarios and suggest future work on hybrid models and broader figurative language tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gargova-etal-2025-comparative">
<titleInfo>
<title>A Comparative Study of Hyperbole Detection Methods: From Rule-Based Approaches through Deep Learning Models to Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="family">Gargova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nevena</namePart>
<namePart type="family">Grigorova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</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 First Workshop on Comparative Performance Evaluation: From Rules to Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Picazo-Izquierdo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Estevanell-Valladares</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>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">Muñoz</namePart>
<namePart type="family">Guillena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="given">García</namePart>
<namePart type="family">Cerdá</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>We address hyperbole detection as a binary classification task, comparing rule-based methods, fine-tuned transformers (BERT, RoBERTa), and large language models (LLMs) in zero-shot and few-shot prompting (Gemini, LLaMA). Fine-tuned transformers achieved the best overall performance, with RoBERTa attaining an F1-score of 0.82. Rule-based methods performed lower (F1 = 0.58) but remain effective in constrained linguistic contexts. LLMs showed mixed results: zero-shot performance was variable, while few-shot prompting notably improved outcomes, reaching F1-scores up to 0.79 without task-specific training data. We discuss the trade-offs between interpretability, computational cost, and data requirements across methods. Our results highlight the promise of LLMs in low-resource scenarios and suggest future work on hybrid models and broader figurative language tasks.</abstract>
<identifier type="citekey">gargova-etal-2025-comparative</identifier>
<location>
<url>https://aclanthology.org/2025.r2lm-1.4/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>30</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparative Study of Hyperbole Detection Methods: From Rule-Based Approaches through Deep Learning Models to Large Language Models
%A Gargova, Silvia
%A Grigorova, Nevena
%A Mitkov, Ruslan
%Y Picazo-Izquierdo, Alicia
%Y Estevanell-Valladares, Ernesto Luis
%Y Mitkov, Ruslan
%Y Guillena, Rafael Muñoz
%Y Cerdá, Raúl García
%S Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F gargova-etal-2025-comparative
%X We address hyperbole detection as a binary classification task, comparing rule-based methods, fine-tuned transformers (BERT, RoBERTa), and large language models (LLMs) in zero-shot and few-shot prompting (Gemini, LLaMA). Fine-tuned transformers achieved the best overall performance, with RoBERTa attaining an F1-score of 0.82. Rule-based methods performed lower (F1 = 0.58) but remain effective in constrained linguistic contexts. LLMs showed mixed results: zero-shot performance was variable, while few-shot prompting notably improved outcomes, reaching F1-scores up to 0.79 without task-specific training data. We discuss the trade-offs between interpretability, computational cost, and data requirements across methods. Our results highlight the promise of LLMs in low-resource scenarios and suggest future work on hybrid models and broader figurative language tasks.
%U https://aclanthology.org/2025.r2lm-1.4/
%P 30-38
Markdown (Informal)
[A Comparative Study of Hyperbole Detection Methods: From Rule-Based Approaches through Deep Learning Models to Large Language Models](https://aclanthology.org/2025.r2lm-1.4/) (Gargova et al., R2LM 2025)
ACL