hhy-huang/GraphJudge

[EMNLP'25 main] This is the official repo for the paper, Can LLMs be Good Graph Judge for Knowledge Graph Construction?

34
/ 100
Emerging

This project helps knowledge engineers and researchers refine automatically generated knowledge graphs. It takes an initial set of text data and candidate knowledge graph triples (subject-predicate-object statements) and outputs a higher-quality, filtered knowledge graph with inaccurate information removed. It's designed for professionals building or evaluating knowledge bases who need to ensure the accuracy of machine-generated facts.

No commits in the last 6 months.

Use this if you need to improve the precision of knowledge graphs automatically extracted from text, especially when dealing with noisy or uncertain data from large language models.

Not ideal if you are looking for a tool to generate knowledge graphs from scratch without a judging or filtering step, or if your primary focus is on other aspects of knowledge graph construction like entity linking or ontology alignment.

knowledge-graph information-extraction data-quality semantic-web natural-language-processing
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 10 / 25

How are scores calculated?

Stars

27

Forks

3

Language

Python

License

MIT

Last pushed

Sep 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hhy-huang/GraphJudge"

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