AutoKG: Efficient Automated Knowledge Graph Generation for Language Models
This addresses the limitation of traditional methods in capturing complex relational dynamics for LLMs, though it appears incremental as it builds on existing techniques.
The paper tackled the problem of linking large language models to knowledge bases by introducing AutoKG, an automated knowledge graph generation method that uses keyword extraction and graph Laplace learning, resulting in more comprehensive and interconnected knowledge retrieval compared to semantic similarity search.
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.