TIFIN India 在 SemEval-2025:利用翻译克服事实核查声明检索中的多语言信息检索挑战
TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval
AI总结:
本研究提出两阶段检索策略,利用大语言模型翻译克服多语言信息检索障碍,在消费级GPU上实现事实核查声明检索,单语和跨语言测试集success@10分别达0.938和0.81025。
摘要:
我们解决了在单语和跨语言环境中检索先前已核查声明这一挑战——鉴于全球虚假信息的普遍性,这是一项关键任务。我们的方法采用两阶段策略:一个基于微调嵌入模型的可靠基线检索系统和一个基于大语言模型的重排序器。我们的主要贡献是展示基于大语言模型的翻译如何能够克服多语言信息检索的障碍。此外,我们专注于确保流水线的大部分可以在消费级GPU上复现。我们最终集成的系统在单语和跨语言测试集上分别取得了0.938和0.81025的success@10分数。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。