We address claim normalization for multilingual misinformation detection - transforming noisy social media posts into clear, verifiable statements across 20 languages. The key contribution demonstrates how systematic decomposition of posts using Who, What, Where, When, Why and How questions enables robust cross-lingual transfer despite training exclusively on English data. Our methodology incorporates finetuning Qwen3-14B using LoRA with the provided dataset after intra-post deduplication, token-level recall filtering for semantic alignment and retrieval-augmented few-shot learning with contextual examples during inference. Our system achieves METEOR scores ranging from 41.16 (English) to 15.21 (Marathi), securing third rank on the English leaderboard and fourth rank for Dutch and Punjabi. The approach shows 41.3% relative improvement in METEOR over baseline configurations and substantial gains over existing methods. Results demonstrate effective cross-lingual generalization for Romance and Germanic languages while maintaining semantic coherence across diverse linguistic structures.

翻译：本文针对多语言虚假信息检测中的主张规范化任务——将包含噪声的社交媒体帖子转化为清晰、可验证的陈述，覆盖20种语言。核心贡献在于展示了如何通过系统性地运用何人、何事、何地、何时、何因及如何（Who, What, Where, When, Why, How）等提问对帖子进行分解，从而在仅使用英语数据训练的情况下实现稳健的跨语言迁移。我们的方法包括：在帖子内去重后，使用提供的数据集通过LoRA对Qwen3-14B模型进行微调；采用基于词元召回率的过滤机制以确保语义对齐；在推理阶段结合检索增强的少样本学习，引入上下文示例。该系统取得的METEOR分数范围从41.16（英语）到15.21（马拉地语），在英语排行榜上位列第三，在荷兰语和旁遮普语排行榜上位列第四。相较于基线配置，该方法在METEOR指标上实现了41.3%的相对提升，并显著优于现有方法。实验结果表明，该方法对罗曼语族和日耳曼语族语言实现了有效的跨语言泛化，同时在不同语言结构中保持了语义连贯性。