用检索+小模型快速标准化多语言假言，13语种中7个夺冠
DS@GT at CheckThat! 2025: A Simple Retrieval-First, LLM-Backed Framework for Claim Normalization
- 先检索训练集最相似样本，否则用GPT-4o-mini动态提示
- 13种语言中7种在单语任务上排名第一，平均得分超基线12%
- 适合多语言事实核查场景，尤其擅长已有语言的快速部署
声明标准化是自动事实核查系统的关键环节，将社交媒体等噪声数据中的声明解析为可验证的规范形式。2025年CheckThat!任务2聚焦于该问题，涵盖20种语言的单语与零样本场景。本文提出一种轻量级‘检索优先、大模型支持’的流水线：若无匹配样本则用GPT-4o-mini进行上下文提示，否则直接检索训练集中最相近的标准化结果。在官方测试集上，该系统在多数单语赛道排名靠前，13种语言中有7种获得第一。但在零样本设置下表现较差，暴露了当前方案的局限性。
原文摘要 · Abstract (English)
Claim normalization is an integral part of any automatic fact-check verification system. It parses the typically noisy claim data, such as social media posts into normalized claims, which are then fed into downstream veracity classification tasks. The CheckThat! 2025 Task 2 focuses specifically on claim normalization and spans 20 languages under monolingual and zero-shot conditions. Our proposed solution consists of a lightweight \emph{retrieval-first, LLM-backed} pipeline, in which we either dynamically prompt a GPT-4o-mini with in-context examples, or retrieve the closest normalization from the train dataset directly. On the official test set, the system ranks near the top for most monolingual tracks, achieving first place in 7 out of of the 13 languages. In contrast, the system underperforms in the zero-shot setting, highlighting the limitation of the proposed solution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。