将大模型与知识图谱结合，实现可解释的智能生成。
Logic Augmented Generation
- 用大模型构建动态知识图谱，按需生成关系和隐含知识。
- 结合知识图谱的逻辑边界，提升生成结果的可靠性。
- 在医疗诊断和气候预测中验证，适合需要可解释性的任务。
语义知识图谱（SKG）面临可扩展性、灵活性、上下文理解及处理非结构化或模糊信息的挑战，但其形式化和结构化知识能通过推理与查询实现高度可解释且可靠的结果。大语言模型（LLMs）克服了这些局限，适用于开放任务和非结构化环境，然而缺乏可解释性和可靠性。为解决LLM与SKG之间的矛盾，本文提出逻辑增强生成（LAG），融合两者优势。LAG将LLM视为反应式连续知识图谱，可按需生成无限关系与隐含知识；而SKG则提供离散的启发式维度，具备明确的逻辑与事实边界。本文在集体智能的两个任务中验证LAG：医学诊断与气候预测。深入理解LAG的特性与局限，对推动涉及隐含知识的各类任务具有重要意义，有助于实现可解释且高效的结果。
原文摘要 · Abstract (English)
Semantic Knowledge Graphs (SKG) face challenges with scalability, flexibility, contextual understanding, and handling unstructured or ambiguous information. However, they offer formal and structured knowledge enabling highly interpretable and reliable results by means of reasoning and querying. Large Language Models (LLMs) overcome those limitations making them suitable in open-ended tasks and unstructured environments. Nevertheless, LLMs are neither interpretable nor reliable. To solve the dichotomy between LLMs and SKGs we envision Logic Augmented Generation (LAG) that combines the benefits of the two worlds. LAG uses LLMs as Reactive Continuous Knowledge Graphs that can generate potentially infinite relations and tacit knowledge on-demand. SKGs are key for injecting a discrete heuristic dimension with clear logical and factual boundaries. We exemplify LAG in two tasks of collective intelligence, i.e., medical diagnostics and climate projections. Understanding the properties and limitations of LAG, which are still mostly unknown, is of utmost importance for enabling a variety of tasks involving tacit knowledge in order to provide interpretable and effective results.
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。