AutoKG: Efficient Automated Knowledge Graph Generation for Language Models

Bohan Chen, Andrea L. Bertozzi
11/22/2023
cs.CL

No official code found. Best implementation: wispcarey/AutoKG (143 stars, MIT, last commit 2026-01-15).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

wispcarey/AutoKGCommunity100%
MIT

Efficient Automated Knowledge Graph Generation for Large Language Models

14324Python, Jupyter NotebookAug 17, 20239 months agoMIT

Similar Papers

GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding

87% match2024

LightKGG: Simple and Efficient Knowledge Graph Generation from Textual Data

86% match2025

Exploring In-Context Learning Capabilities of Foundation Models for Generating Knowledge Graphs from Text

86% match2023

Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings

85% match2024

Semantic Web: Past, Present, and Future (with Machine Learning on Knowledge Graphs and Language Models on Knowledge Graphs)

85% match1 repo52024

Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs

85% match2025

Cite this paper

@article{chen2023autokg,
  title  = {AutoKG: Efficient Automated Knowledge Graph Generation for Language Models},
  author = {Bohan Chen and Andrea L. Bertozzi},
  year   = {2023},
  eprint = {2311.14740},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.14740v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.14740.svg)](https://codeofpaper.com/paper/2311.14740)

Discussion