用分步提示法提升多语言新闻叙事分类准确率
GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification
- 分三步引导大模型：先分领域，再定主叙事，最后判子叙事
- 在英语测试集上超越28支队伍，排名第一
- 适合需要跨语言信息分析的研究者与政策制定者
在线新闻的泛滥和虚假信息的传播加剧了对自动数据分析方法的需求。叙事分类正成为关键任务，因为识别网络上的言论内容对事实核查员、政策制定者及其他信息研究专业人员至关重要。本文介绍了我们参与SemEval 2025 Task 10 Subtask 2的解决方案，该任务旨在对多语言新闻文章进行预定义的两级叙事分类（主叙事与子叙事）。我们提出了层级三步提示法（H3Prompt），采用分步式大语言模型（LLM）提示策略：首先将文章归入乌克兰-俄罗斯战争或气候变化两个领域之一，接着识别最相关的主叙事，最后分配子叙事。该方法在英语测试集上位列全球28支参赛队伍中的第一名。代码已开源：https://github.com/GateNLP/H3Prompt。
原文摘要 · Abstract (English)
The proliferation of online news and the increasing spread of misinformation necessitate robust methods for automatic data analysis. Narrative classification is emerging as a important task, since identifying what is being said online is critical for fact-checkers, policy markers and other professionals working on information studies. This paper presents our approach to SemEval 2025 Task 10 Subtask 2, which aims to classify news articles into a pre-defined two-level taxonomy of main narratives and sub-narratives across multiple languages. We propose Hierarchical Three-Step Prompting (H3Prompt) for multilingual narrative classification. Our methodology follows a three-step Large Language Model (LLM) prompting strategy, where the model first categorises an article into one of two domains (Ukraine-Russia War or Climate Change), then identifies the most relevant main narratives, and finally assigns sub-narratives. Our approach secured the top position on the English test set among 28 competing teams worldwide. The code is available at https://github.com/GateNLP/H3Prompt.
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。