控制工程研究成果的快速增长需要新的方法来结构化和形式化领域知识。本文简要描述了一种LLM支持的方法,用于半自动生成形式化知识表示,该方法结合了人类可读性、机器可解释性和更强的表达能力。基于Imperative Representation of Knowledge (PyIRK)框架,我们展示了语言模型如何协助将自然语言描述和数学定义(以LaTeX源代码形式提供)转化为形式化知识图谱。作为首个应用,我们展示了生成“交互式语义层”以增强源文档,从而促进知识转移。从我们的角度来看,这有助于实现控制工程领域易于访问、协作和可验证的知识库的愿景。
英文摘要:
The rapid growth of research output in control engineering calls for new approaches to structure and formalize domain knowledge. This paper briefly describes an LLM-supported method for semi-automated generation of formal knowledge representations that combine human readability with machine interpretability and increased expressiveness. Based on the Imperative Representation of Knowledge (PyIRK) framework, we demonstrate how language models can assist in transforming natural-language descriptions and mathematical definitions (available as LaTeX source code) into a formalized knowledge graph. As a first application we present the generation of an ``interactive semantic layer'' to enhance the source documents in order to facilitate knowledge transfer. From our perspective this contributes to the vision of easily accessible, collaborative, and verifiable knowledge bases for the control engineering domain.
The KB paradigm and its application to interactive configuration
KU Leuven(鲁汶大学)
知识库范式旨在以丰富的形式语言表达领域知识,并将该领域知识作为知识库,通过应用多种形式的推理来解决领域中出现的各种问题和任务。因此,该范式在信息和问题解决之间应用了严格的关注分离。在本文中,我们分析的原则和可行性的知识库范例的背景下,一类重要的应用程序:交互式配置问题。在交互式配置问题中,在约束条件下搜索相关对象的配置,其中系统帮助用户达到预期的配置。业界普遍认为,针对这些问题的良好软件解决方案非常难以开发。我们从知识库范式的角度来研究这些问题。我们表明,在这个领域中的多种功能可以通过应用不同形式的逻辑推理的配置域的正式规范。我们报告的概念证明这种方法在现实生活中的应用与银行公司。逻辑程序设计理论与实践(Theory and Practice of Logic Programming,TPLP)
FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区);City Univeristy of Hong Kong(香港城市大学);Sun Yat-sen University(中山大学);The University of Hong Kong(香港大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);MBZUAI(Mohamed bin Zayed 人工智能大学);DarkMatter AI Research(DarkMatter AI 研究院)
Collecting Interactive Multi-modal Datasets for Grounded Language Understanding
Microsoft Research(微软研究院);University of Waterloo(滑铁卢大学);Meta Research(Meta研究院);Moscow Institute of Physics Technology(莫斯科物理技术学院);Artificial Intelligence Research Institute(人工智能研究院)