用AI解析维基百科科学文章的修订史，揭示知识演化脉络
WikiSTAR: A System for Shedding Light on the Hidden History of Scientific Wikipedia Articles
- 用大模型+专家设计标签体系识别科学类编辑类型
- 可逐条追踪修改细节，也能看整体趋势变化
- 适合科研人员、历史学者分析科学认知演进
维基百科在塑造公众科学认知方面起关键作用，其开放的修订历史是科学知识演进的独特记录。然而，大量常规编辑掩盖了具有科学意义的改动，导致每篇文章的科学历史难以察觉。我们提出 WikiSTAR（科学文章修订追踪系统），通过一个由专家设计的多标签分类体系与大语言模型结合，首先对编辑类型进行标注，如技术术语添加、新研究发现引入及科学叙事变更。随后，借助交互式视图，用户可在任意粒度上追溯文章完整修订历史——从整体趋势中观察科学内容何时、在何部分被添加或完善，到具体单条编辑，展示此前无法实现的知识演化尺度。在三个领域的专家用户研究中，参与者发现新规律并提出新的研究问题，实现了以往难以开展的分析。我们已开源系统、代码及人工标注基准数据集。
原文摘要 · Abstract (English)
Wikipedia plays a key role in shaping public understanding of science, and its openly accessible revision history is a unique record of how scientific knowledge evolves over time. Yet scientifically meaningful revisions are obscured by the sheer volume of routine edits, leaving each article's scientific history hidden. We present WikiSTAR (Scientific Tracking of Article Revisions), an interactive system for exploring scientifically meaningful changes across an article's revision history. Using an LLM classifier with an expert-designed multi-label taxonomy, WikiSTAR first tags edit types such as the addition of technical terms, new research findings, and changes in scientific narrative. Then, through interactive views, an article's full revision history can be traced at any granularity - from aggregate trends that reveal when and in which sections scientific content was added or refined, down to individual edits - showing how scientific knowledge develops at a scale previously impossible. In a user study, experts from three domains found that WikiSTAR surfaced new patterns and research questions and enabled previously impractical analyses. We release our system, code and a human-annotated benchmark.
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。