Magic Markup：利用大语言模型维护文档外部标记
Magic Markup: Maintaining Document-External Markup with an LLM
AI总结：
该研究提出Magic Markup系统，借助大语言模型智能体为修改后的程序重新打外部标签，无需文档内显式标记，同时给出问题定义、合成基准套件及生成器，系统准确率达90%，可并行以5秒/标签的速度替换标签，拓展了文档标注的应用场景。
摘要：
文本（包括程序）通常具备人类可读的语义结构。过去，要通过编程方式获取这些语义，需要在文档内添加显式标签。尤其在文本具备执行语义的系统中，这意味着该功能是需主动启用的特性，难以妥善支持。如今，语言模型提供了新方法：可借助模型类人的语义理解能力，将元数据绑定到不断变化的文本中的实体上，且对文档结构无要求。该方法拓展了文档标注的应用场景，而文档标注是程序编写、调试、维护和展示中的基础操作。我们提出了一个系统，它采用智能体对修改后的程序重新打标签，使丰富的标注能随着代码演进自动跟随。我们还给出了正式的问题定义、一个经验性合成基准测试套件，以及我们的基准生成器。我们的系统在基准测试上达到90%的准确率，并且能以每个标签5秒的速度并行替换文档的标签。尽管仍有很大的提升空间，但我们发现其性能已足够可靠，足以支撑对相关应用的进一步探索。
英文摘要：
Text documents, including programs, typically have human-readable semantic structure. Historically, programmatic access to these semantics has required explicit in-document tagging. Especially in systems where the text has an execution semantics, this means it is an opt-in feature that is hard to support properly. Today, language models offer a new method: metadata can be bound to entities in changing text using a model's human-like understanding of semantics, with no requirements on the document structure. This method expands the applications of document annotation, a fundamental operation in program writing, debugging, maintenance, and presentation. We contribute a system that employs an intelligent agent to re-tag modified programs, enabling rich annotations to automatically follow code as it evolves. We also contribute a formal problem definition, an empirical synthetic benchmark suite, and our benchmark generator. Our system achieves an accuracy of 90% on our benchmarks and can replace a document's tags in parallel at a rate of 5 seconds per tag. While there remains significant room for improvement, we find performance reliable enough to justify further exploration of applications.
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。
