@inproceedings{bell-2025-less,
title = "Less Can be More: An Empirical Evaluation of Small and Large Language Models for Sentence-level Claim Detection",
author = "Bell, Andrew",
editor = "Akhtar, Mubashara and
Aly, Rami and
Christodoulopoulos, Christos and
Cocarascu, Oana and
Guo, Zhijiang and
Mittal, Arpit and
Schlichtkrull, Michael and
Thorne, James and
Vlachos, Andreas",
booktitle = "Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.fever-1.6/",
doi = "10.18653/v1/2025.fever-1.6",
pages = "85--90",
ISBN = "978-1-959429-53-1",
abstract = "Sentence-level claim detection is a critical first step in the fact-checking process. While Large Language Models (LLMs) seem well-suited for claim detection, their computational cost poses challenges for real-world deployment. This paper investigates the effectiveness of both small and large pretrained Language Models for the task of claim detection. We conduct a comprehensive empirical evaluation using BERT, ModernBERT, RoBERTa, Llama, and ChatGPT-based models. Our results reveal that smaller models, when finetuned appropriately, can achieve competitive performance with significantly lower computational overhead on in-domain tasks. Notably, we also find that BERT-based models transfer poorly on sentence-level claim detection in out-of-domain tasks. We discuss the implications of these findings for practitioners and highlight directions for future research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bell-2025-less">
<titleInfo>
<title>Less Can be More: An Empirical Evaluation of Small and Large Language Models for Sentence-level Claim Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Bell</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 Eighth Fact Extraction and VERification Workshop (FEVER)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mubashara</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rami</namePart>
<namePart type="family">Aly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Cocarascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijiang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpit</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Schlichtkrull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Thorne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</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">978-1-959429-53-1</identifier>
</relatedItem>
<abstract>Sentence-level claim detection is a critical first step in the fact-checking process. While Large Language Models (LLMs) seem well-suited for claim detection, their computational cost poses challenges for real-world deployment. This paper investigates the effectiveness of both small and large pretrained Language Models for the task of claim detection. We conduct a comprehensive empirical evaluation using BERT, ModernBERT, RoBERTa, Llama, and ChatGPT-based models. Our results reveal that smaller models, when finetuned appropriately, can achieve competitive performance with significantly lower computational overhead on in-domain tasks. Notably, we also find that BERT-based models transfer poorly on sentence-level claim detection in out-of-domain tasks. We discuss the implications of these findings for practitioners and highlight directions for future research.</abstract>
<identifier type="citekey">bell-2025-less</identifier>
<identifier type="doi">10.18653/v1/2025.fever-1.6</identifier>
<location>
<url>https://aclanthology.org/2025.fever-1.6/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>85</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Less Can be More: An Empirical Evaluation of Small and Large Language Models for Sentence-level Claim Detection
%A Bell, Andrew
%Y Akhtar, Mubashara
%Y Aly, Rami
%Y Christodoulopoulos, Christos
%Y Cocarascu, Oana
%Y Guo, Zhijiang
%Y Mittal, Arpit
%Y Schlichtkrull, Michael
%Y Thorne, James
%Y Vlachos, Andreas
%S Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 978-1-959429-53-1
%F bell-2025-less
%X Sentence-level claim detection is a critical first step in the fact-checking process. While Large Language Models (LLMs) seem well-suited for claim detection, their computational cost poses challenges for real-world deployment. This paper investigates the effectiveness of both small and large pretrained Language Models for the task of claim detection. We conduct a comprehensive empirical evaluation using BERT, ModernBERT, RoBERTa, Llama, and ChatGPT-based models. Our results reveal that smaller models, when finetuned appropriately, can achieve competitive performance with significantly lower computational overhead on in-domain tasks. Notably, we also find that BERT-based models transfer poorly on sentence-level claim detection in out-of-domain tasks. We discuss the implications of these findings for practitioners and highlight directions for future research.
%R 10.18653/v1/2025.fever-1.6
%U https://aclanthology.org/2025.fever-1.6/
%U https://doi.org/10.18653/v1/2025.fever-1.6
%P 85-90
Markdown (Informal)
[Less Can be More: An Empirical Evaluation of Small and Large Language Models for Sentence-level Claim Detection](https://aclanthology.org/2025.fever-1.6/) (Bell, FEVER 2025)
ACL