Knowledge-aware-AI/GPTKB

Code for KB construction from LLMs - ACL 2025 paper: "Enabling LLM Knowledge Analysis via Extensive Materialization""

30
/ 100
Emerging

This project helps researchers analyze and understand the vast amount of information contained within large language models like GPT-4.1. It takes a large language model and outputs a structured knowledge base of facts, organized as 'triples' (subject-predicate-object). This is for natural language processing researchers or Semantic Web specialists who want to study how LLMs store and organize their knowledge, or to build new knowledge bases more efficiently.

No commits in the last 6 months.

Use this if you are an NLP or Semantic Web researcher interested in extracting, analyzing, and structuring the explicit factual knowledge embedded within large language models.

Not ideal if you are looking for a tool to directly enhance an existing application's knowledge base or for everyday data extraction tasks without a research focus.

knowledge-base-construction large-language-model-analysis semantic-web-research natural-language-processing information-extraction
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

Python

License

CC-BY-4.0

Last pushed

Oct 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Knowledge-aware-AI/GPTKB"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.