AutoKG: Efficient Automated Knowledge Graph Generation for Language Models
AutoKG: Efficient Automated Knowledge Graph Generation for Language Models
复制标题
DOI：
10.1109/bigdata59044.2023.10386454
复制
发表时间：
2023-11
期刊：
影响因子：
--
通讯作者：
Bohan Chen;Andrea L. Bertozzi
中科院分区：
文献类型：
--
作者：
Bohan Chen;Andrea L. Bertozzi
通过语义相似性搜索将大型语言模型（LLM）链接到知识库的传统方法通常无法捕获复杂的关系动态。为了解决这些限制，我们引入了 AutoKG，一种轻量级且高效的自动化知识图（KG）构建方法。对于由文本块组成的给定知识库，AutoKG 首先使用 LLM 提取关键字，然后使用图拉普拉斯学习评估每对关键字之间的关系权重。我们采用结合矢量相似性和基于图的关联的混合搜索方案来丰富法学硕士的回答。初步实验表明，与语义相似性搜索相比，AutoKG 提供了更全面、更互联的知识检索机制，从而增强了法学硕士生成更有洞察力和相关性输出的能力。
Traditional methods of linking large language models (LLMs) to knowledge bases via the semantic similarity search often fall short of capturing complex relational dynamics. To address these limitations, we introduce AutoKG, a lightweight and efficient approach for automated knowledge graph (KG) construction. For a given knowledge base consisting of text blocks, AutoKG first extracts keywords using a LLM and then evaluates the relationship weight between each pair of keywords using graph Laplace learning. We employ a hybrid search scheme combining vector similarity and graph-based associations to enrich LLM responses. Preliminary experiments demonstrate that AutoKG offers a more comprehensive and interconnected knowledge retrieval mechanism compared to the semantic similarity search, thereby enhancing the capabilities of LLMs in generating more insightful and relevant outputs.