KGGen: Extracting Knowledge Graphs from Plain Text with Language Models

2025/02/14 by Baichuan Mo, Belinda Mo, Mo, Belinda +18 · 1 voice · 21 citations
Computer Science · #Artificial intelligence #Computer science #Linguistics #Natural Language Processing Techniques #Natural language processing #Philosophy #Plain language #Plain text #Semantic Web and Ontologies #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2502.09956

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/02/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Recent interest in building foundation models for KGs has highlighted a fundamental challenge: knowledge-graph data is relatively scarce. The best-known KGs are primarily human-labeled, created by pattern-matching, or extracted using early NLP techniques. While human-generated KGs are in short supply, automatically extracted KGs are of questionable quality. We present a solution to this data scarcity problem in the form of a text-to-KG generator (KGGen), a package that uses language models to create high-quality graphs from plaintext. Unlike other KG extractors, KGGen clusters related entities to reduce sparsity in extracted KGs. KGGen is available as a Python library (pip install kg-gen), making it accessible to everyone. Along with KGGen, we release the first benchmark, Measure of of Information in Nodes and Edges (MINE), that tests an extractor's ability to produce a useful KG from plain text. We benchmark our new tool against existing extractors and demonstrate far superior performance.

Cited by

• PEARL: Auditable Repair for Scientific Reasoning Graph Extraction
• Interpretable Column Annotation with LLM-Symbolized Decision Process Materialization
• Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning
• Ontology-Based Knowledge Graph Framework for Industrial Standard Documents via Hierarchical and Propositional Structuring
• gHAWK: Local and Global Structure Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphs
• InvertiTune: High-Quality Data Synthesis for Cost-Effective Single-Shot Text-to-Knowledge Graph Generation
• HalluGraph: Auditable Hallucination Detection for Legal RAG Systems via Knowledge Graph Alignment
• Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models
• SAM Guided Semantic and Motion Changed Region Mining for Remote Sensing Change Captioning
• AI Consciousness and Existential Risk
• BambooKG: A Neurobiologically-inspired Frequency-Weight Knowledge Graph
• LightKGG: Simple and Efficient Knowledge Graph Generation from Textual Data
• LLM-empowered knowledge graph construction: A survey
• AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
• AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction
• Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling
• ODKE+: Ontology-Guided Open-Domain Knowledge Extraction with LLMs
• CLARIFY: A Specialist-Generalist Framework for Accurate and Lightweight Dermatological Visual Question Answering
• Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework
• The Semantic Units Framework, a technology-agnostic representational approach to FAIR and CLEAR knowledge infrastructures
• Rosetta Statements: simplifying FAIR knowledge graph construction with a user-centred approach
• EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge
• Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction
• RAKG:Document-level Retrieval Augmented Knowledge Graph Construction

Discussions

• KGGen: Extracting Knowledge Graphs from Plain Text with Language Models [hn, 20 points, 4 comments]

Related

• LightKGG: Simple and Efficient Knowledge Graph Generation from Textual Data
• Knowledge Graph Generation From Text
• KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models
• LambdaKG: A Library for Pre-trained Language Model-Based Knowledge Graph Embeddings
• GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation