@inproceedings{devadiga-etal-2025-tifin,
title = "{TIFIN} {I}ndia at {S}em{E}val-2025: Harnessing Translation to Overcome Multilingual {IR} Challenges in Fact-Checked Claim Retrieval",
author = "Devadiga, Prasanna and
Suneesh, Arya and
Rajpoot, Pawan and
Hazarika, Bharatdeep and
Baliga, Aditya",
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-1.299/",
pages = "2297--2304",
ISBN = "979-8-89176-273-2",
abstract = "We address the challenge of retrieving previously fact-checked claims in mono-lingual and cross-lingual settings - a critical task given the global prevalence of disinformation. Our approach follows a two-stage strategy: a reliable baseline retrieval system using a fine-tuned embedding model and an LLM-based reranker. Our key contribution is demonstrating how LLM-based translation can overcome the hurdles of multilingual information retrieval. Additionally, we focus on ensuring that the bulk of the pipeline can be replicated on a consumer GPU. Our final integrated system achieved a success@10 score of 0.938 ({\textasciitilde}0.94) and 0.81025 on the monolingual and crosslingual test sets respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="devadiga-etal-2025-tifin">
<titleInfo>
<title>TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prasanna</namePart>
<namePart type="family">Devadiga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arya</namePart>
<namePart type="family">Suneesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Rajpoot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharatdeep</namePart>
<namePart type="family">Hazarika</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Baliga</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>We address the challenge of retrieving previously fact-checked claims in mono-lingual and cross-lingual settings - a critical task given the global prevalence of disinformation. Our approach follows a two-stage strategy: a reliable baseline retrieval system using a fine-tuned embedding model and an LLM-based reranker. Our key contribution is demonstrating how LLM-based translation can overcome the hurdles of multilingual information retrieval. Additionally, we focus on ensuring that the bulk of the pipeline can be replicated on a consumer GPU. Our final integrated system achieved a success@10 score of 0.938 (~0.94) and 0.81025 on the monolingual and crosslingual test sets respectively.</abstract>
<identifier type="citekey">devadiga-etal-2025-tifin</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.299/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2297</start>
<end>2304</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval
%A Devadiga, Prasanna
%A Suneesh, Arya
%A Rajpoot, Pawan
%A Hazarika, Bharatdeep
%A Baliga, Aditya
%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 devadiga-etal-2025-tifin
%X We address the challenge of retrieving previously fact-checked claims in mono-lingual and cross-lingual settings - a critical task given the global prevalence of disinformation. Our approach follows a two-stage strategy: a reliable baseline retrieval system using a fine-tuned embedding model and an LLM-based reranker. Our key contribution is demonstrating how LLM-based translation can overcome the hurdles of multilingual information retrieval. Additionally, we focus on ensuring that the bulk of the pipeline can be replicated on a consumer GPU. Our final integrated system achieved a success@10 score of 0.938 (~0.94) and 0.81025 on the monolingual and crosslingual test sets respectively.
%U https://aclanthology.org/2025.semeval-1.299/
%P 2297-2304
Markdown (Informal)
[TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval](https://aclanthology.org/2025.semeval-1.299/) (Devadiga et al., SemEval 2025)
ACL