对比中英文讽刺新闻检测，发现结构化推理能显著提升模型效果
Comparison of Multilingual and Bilingual Models for Satirical News Detection of Arabic and English
- 用链式思维提示（CoT）增强模型推理能力
- Jais-chat在英语讽刺新闻检测上达到80%的F1分数
- 适合关注多语言内容安全与推理机制的研究者
讽刺新闻是真实新闻掺杂幽默或夸张内容，常模仿真实新闻的格式和风格。但因其易被误判为虚假信息，尤其对不同文化背景的用户而言，识别难度大。本研究针对英阿双语环境下讽刺新闻检测挑战，采用Jais-chat(13B)与LLaMA-2-chat(7B)两个模型，探索零样本与链式思维（CoT）提示方法。结果显示，使用CoT提示时，Jais-chat在英语任务中表现最优，F1得分为80%。该结果凸显结构化推理在提升上下文理解上的关键作用，对复杂任务如讽刺识别尤为重要。
原文摘要 · Abstract (English)
Satirical news is real news combined with a humorous comment or exaggerated content, and it often mimics the format and style of real news. However, satirical news is often misunderstood as misinformation, especially by individuals from different cultural and social backgrounds. This research addresses the challenge of distinguishing satire from truthful news by leveraging multilingual satire detection methods in English and Arabic. We explore both zero-shot and chain-of-thought (CoT) prompting using two language models, Jais-chat(13B) and LLaMA-2-chat(7B). Our results show that CoT prompting offers a significant advantage for the Jais-chat model over the LLaMA-2-chat model. Specifically, Jais-chat achieved the best performance, with an F1-score of 80\% in English when using CoT prompting. These results highlight the importance of structured reasoning in CoT, which enhances contextual understanding and is vital for complex tasks like satire detection.
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。