RManLuo/graph-constrained-reasoning

Official Implementation of ICML 2025 Paper: "Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models".

43
/ 100
Emerging

This framework helps AI developers integrate structured knowledge from existing knowledge graphs with the flexible reasoning capabilities of large language models. It takes a knowledge graph and a large language model as input, ensuring the LLM generates accurate, verifiable reasoning paths and answers directly grounded in the graph's facts, eliminating hallucinations. The primary users are AI engineers or researchers building question-answering systems or knowledge-driven AI applications.

238 stars. No commits in the last 6 months.

Use this if you need to build AI systems that provide accurate, verifiable answers by reasoning directly over a knowledge graph, preventing the LLM from generating false or unsupported information.

Not ideal if your application does not involve structured knowledge graphs or if you do not require strict factual grounding for LLM outputs.

knowledge-graphs large-language-models reasoning-systems ai-development fact-checking-ai
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

238

Forks

25

Language

Python

License

MIT

Last pushed

May 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/RManLuo/graph-constrained-reasoning"

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