TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval

Prasanna Devadiga, Arya Suneesh, Pawan Rajpoot, Bharatdeep Hazarika, Aditya Baliga


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.
Anthology ID:
2025.semeval-1.299
Volume:
Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
Month:
July
Year:
2025
Address:
Vienna, Austria
Editors:
Sara Rosenthal, Aiala Rosá, Debanjan Ghosh, Marcos Zampieri
Venues:
SemEval | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2297–2304
Language:
URL:
https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.299/
DOI:
Bibkey:
Cite (ACL):
Prasanna Devadiga, Arya Suneesh, Pawan Rajpoot, Bharatdeep Hazarika, and Aditya Baliga. 2025. TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2297–2304, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):
TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval (Devadiga et al., SemEval 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.299.pdf