@inproceedings{panchendrarajan-etal-2025-claimcatchers,
title = "{C}laim{C}atchers at {S}em{E}val-2025 Task 7: Sentence Transformers for Claim Retrieval",
author = "Panchendrarajan, Rrubaa and
Frade, Rafael and
Zubiaga, Arkaitz",
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.63/",
pages = "455--462",
ISBN = "979-8-89176-273-2",
abstract = "Retrieving previously fact-checked claims from verified databases has become a crucial area of research in automated fact-checking, given the impracticality of manual verification of massive online content. To address this challenge, SemEval 2025 Task 7 focuses on multilingual previously fact-checked claim retrieval. This paper presents the experiments conducted for this task, evaluating the effectiveness of various sentence transformer models{---}ranging from 22M to 9B parameters{---}in conjunction with retrieval strategies such as nearest neighbor search and reranking techniques. Further, we explore the impact of learning context-specific text representation via finetuning these models. Our results demonstrate that smaller and medium-sized models, when optimized with effective finetuning and reranking, can achieve retrieval accuracy comparable to larger models, highlighting their potential for scalable and efficient misinformation detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="panchendrarajan-etal-2025-claimcatchers">
<titleInfo>
<title>ClaimCatchers at SemEval-2025 Task 7: Sentence Transformers for Claim Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rrubaa</namePart>
<namePart type="family">Panchendrarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Frade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arkaitz</namePart>
<namePart type="family">Zubiaga</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 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</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">979-8-89176-273-2</identifier>
</relatedItem>
<abstract>Retrieving previously fact-checked claims from verified databases has become a crucial area of research in automated fact-checking, given the impracticality of manual verification of massive online content. To address this challenge, SemEval 2025 Task 7 focuses on multilingual previously fact-checked claim retrieval. This paper presents the experiments conducted for this task, evaluating the effectiveness of various sentence transformer models—ranging from 22M to 9B parameters—in conjunction with retrieval strategies such as nearest neighbor search and reranking techniques. Further, we explore the impact of learning context-specific text representation via finetuning these models. Our results demonstrate that smaller and medium-sized models, when optimized with effective finetuning and reranking, can achieve retrieval accuracy comparable to larger models, highlighting their potential for scalable and efficient misinformation detection.</abstract>
<identifier type="citekey">panchendrarajan-etal-2025-claimcatchers</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.63/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>455</start>
<end>462</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ClaimCatchers at SemEval-2025 Task 7: Sentence Transformers for Claim Retrieval
%A Panchendrarajan, Rrubaa
%A Frade, Rafael
%A Zubiaga, Arkaitz
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F panchendrarajan-etal-2025-claimcatchers
%X Retrieving previously fact-checked claims from verified databases has become a crucial area of research in automated fact-checking, given the impracticality of manual verification of massive online content. To address this challenge, SemEval 2025 Task 7 focuses on multilingual previously fact-checked claim retrieval. This paper presents the experiments conducted for this task, evaluating the effectiveness of various sentence transformer models—ranging from 22M to 9B parameters—in conjunction with retrieval strategies such as nearest neighbor search and reranking techniques. Further, we explore the impact of learning context-specific text representation via finetuning these models. Our results demonstrate that smaller and medium-sized models, when optimized with effective finetuning and reranking, can achieve retrieval accuracy comparable to larger models, highlighting their potential for scalable and efficient misinformation detection.
%U https://aclanthology.org/2025.semeval-1.63/
%P 455-462
Markdown (Informal)
[ClaimCatchers at SemEval-2025 Task 7: Sentence Transformers for Claim Retrieval](https://aclanthology.org/2025.semeval-1.63/) (Panchendrarajan et al., SemEval 2025)
ACL