@inproceedings{benchert-etal-2025-caidas,
title = "{CAIDAS} at {S}em{E}val-2025 Task 7: Enriching Sparse Datasets with {LLM}-Generated Content for Improved Information Retrieval",
author = "Benchert, Dominik and
Me{\ss}linger, Severin and
Goller, Sven and
Kaiser, Jonas and
Pfister, Jan and
Hotho, Andreas",
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-1.214/",
pages = "1623--1638",
ISBN = "979-8-89176-273-2",
abstract = "The focus of SemEval-2024 Task 7 is the retrieval of relevant fact-checks for social media posts across multiple languages. We approach this task with an enhanced bi-encoder retrieval setup, which is designed to match social media posts with relevant fact-checks using synthetic data from LLMs. We explored and analyzed two main approaches for generating synthetic posts. Either based on existing fact-checks or on existing posts. Our approach achieved an S@10 score of 89.53{\%} for the monolingual task and 74.48{\%} for the crosslingual task, ranking 16th out of 28 and 13th out of 29, respectively. Without data augmentation, scores would have been 88.69 (17th) and 72.93 (15th)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="benchert-etal-2025-caidas">
<titleInfo>
<title>CAIDAS at SemEval-2025 Task 7: Enriching Sparse Datasets with LLM-Generated Content for Improved Information Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Benchert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Severin</namePart>
<namePart type="family">Meßlinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sven</namePart>
<namePart type="family">Goller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Kaiser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Pfister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Hotho</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>The focus of SemEval-2024 Task 7 is the retrieval of relevant fact-checks for social media posts across multiple languages. We approach this task with an enhanced bi-encoder retrieval setup, which is designed to match social media posts with relevant fact-checks using synthetic data from LLMs. We explored and analyzed two main approaches for generating synthetic posts. Either based on existing fact-checks or on existing posts. Our approach achieved an S@10 score of 89.53% for the monolingual task and 74.48% for the crosslingual task, ranking 16th out of 28 and 13th out of 29, respectively. Without data augmentation, scores would have been 88.69 (17th) and 72.93 (15th).</abstract>
<identifier type="citekey">benchert-etal-2025-caidas</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.214/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1623</start>
<end>1638</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAIDAS at SemEval-2025 Task 7: Enriching Sparse Datasets with LLM-Generated Content for Improved Information Retrieval
%A Benchert, Dominik
%A Meßlinger, Severin
%A Goller, Sven
%A Kaiser, Jonas
%A Pfister, Jan
%A Hotho, Andreas
%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 benchert-etal-2025-caidas
%X The focus of SemEval-2024 Task 7 is the retrieval of relevant fact-checks for social media posts across multiple languages. We approach this task with an enhanced bi-encoder retrieval setup, which is designed to match social media posts with relevant fact-checks using synthetic data from LLMs. We explored and analyzed two main approaches for generating synthetic posts. Either based on existing fact-checks or on existing posts. Our approach achieved an S@10 score of 89.53% for the monolingual task and 74.48% for the crosslingual task, ranking 16th out of 28 and 13th out of 29, respectively. Without data augmentation, scores would have been 88.69 (17th) and 72.93 (15th).
%U https://aclanthology.org/2025.semeval-1.214/
%P 1623-1638
Markdown (Informal)
[CAIDAS at SemEval-2025 Task 7: Enriching Sparse Datasets with LLM-Generated Content for Improved Information Retrieval](https://aclanthology.org/2025.semeval-1.214/) (Benchert et al., SemEval 2025)
ACL