TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval
This addresses the challenge of multilingual information retrieval for fact-checking, which is incremental as it builds on existing methods with translation enhancements.
The paper tackled the problem of retrieving previously fact-checked claims in monolingual and crosslingual settings to combat disinformation, achieving success@10 scores of 0.938 and 0.81025 on test sets.
We address the challenge of retrieving previously fact-checked claims in monolingual and crosslingual 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 and 0.81025 on the monolingual and crosslingual test sets, respectively.