面向嘈杂多语言社交媒体帖子的推理引导声明规范化
Reasoning-Guided Claim Normalization for Noisy Multilingual Social Media Posts
AI总结:
本文提出基于六何问题分解与推理引导的声明规范化方法,通过LoRA微调Qwen3-14B并结合检索增强少样本学习,在仅用英语训练的情况下实现20种语言的跨语言迁移,在多个排行榜上取得领先成绩。
摘要:
我们针对多语言错误信息检测中的声明规范化问题展开研究,目标是将20种语言中嘈杂的社交媒体帖子转换为清晰、可验证的陈述。关键贡献在于证明了利用“谁、什么、何地、何时、为何、如何”六类问题对帖子进行系统化分解,能够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:使用LoRA对Qwen3-14B进行微调,并在帖子内部去重、基于词元级召回过滤进行语义对齐,以及在推理阶段结合上下文示例的检索增强少样本学习。我们的系统在METEOR指标上取得了从41.16(英语)到15.21(马拉地语)不等的成绩,在英语排行榜上获得第三名,在荷兰语和旁遮普语上获得第四名。该方法相比基线配置在METEOR上实现了41.3%的相对提升,并显著优于现有方法。结果表明,该方法对罗曼语族和日耳曼语族语言具有有效的跨语言泛化能力,同时在不同语言结构之间保持了语义连贯性。
英文摘要:
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.
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。