用金字塔原理提升大模型与知识图谱的推理对齐，减少幻觉。
Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphs
- 基于金字塔原理构建分层结构，引导问题理解与推理。
- 在问答任务中相较基线提升26.70%和26.78%准确率。
- 适合需要高可靠推理的智能问答系统开发者。
大型语言模型（LLMs）虽具备强大推理能力，但易生成错误信息，即“幻觉”。尽管引入外部知识图谱（KGs）可部分缓解此问题，现有方法多将KG视为静态知识库，忽视了KG与LLM知识间的本质差异，且未充分挖掘KG内在的推理潜力。为此，我们提出金字塔驱动对齐（PDA）框架，实现LLMs与KGs的无缝融合。PDA利用金字塔原理构建分层金字塔结构，以反映输入问题并生成更受验证的演绎知识，从而增强两者间对齐，实现更连贯的集成。此外，PDA采用递归机制，激发KG的深层推理能力，显著提升问答任务中的知识检索精度。实验结果表明，相较于先进基线，PDA在性能上取得显著优势，最高提升达26.70%和26.78%。
原文摘要 · Abstract (English)
Large Language Models (LLMs) possess impressive reasoning abilities but are prone to generating incorrect information, often referred to as hallucinations. While incorporating external Knowledge Graphs (KGs) can partially mitigate this issue, existing methods primarily treat KGs as static knowledge repositories, overlooking the critical disparity between KG and LLM knowledge, and failing to fully exploit the reasoning capabilities inherent in KGs. To address these limitations, we propose Pyramid-Driven Alignment (PDA), a novel framework for seamlessly integrating LLMs with KGs. PDA utilizes Pyramid Principle analysis to construct a hierarchical pyramid structure. This structure is designed to reflect the input question and generate more validated deductive knowledge, thereby enhancing the alignment of LLMs and KGs and ensuring more cohesive integration. Furthermore, PDA employs a recursive mechanism to harness the underlying reasoning abilities of KGs, resulting in more accurate knowledge retrieval for question-answering tasks. Our experimental results reveal a substantial performance advantage of PDA over state-of-the-art baselines, with improvements reaching 26.70% and 26.78%.
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。