RManLuo/reasoning-on-graphs

Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning"

37
/ 100
Emerging

Implements a planning-retrieval-reasoning pipeline that grounds LLM reasoning in knowledge graphs by first generating relation paths as faithful plans, then retrieving corresponding subgraphs from Freebase for answer generation. Supports plug-and-play integration with multiple LLMs (GPT-3.5, Llama2, Alpaca, Flan-T5) via prompt-based inference, with automatic model weight and dataset downloads from Hugging Face. Includes interpretable reasoning capabilities that expose the intermediate reasoning paths used by the model for transparency.

497 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 18 / 25

How are scores calculated?

Stars

497

Forks

57

Language

Python

License

MIT

Last pushed

Mar 05, 2025

Commits (30d)

0

Get this data via API

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

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