SteveTANTAN/PoG
[WWW 2025] Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning
This project helps researchers and data scientists improve the accuracy of large language models (LLMs) when answering complex questions. By integrating an LLM with a knowledge graph like Freebase, it takes natural language questions and produces more precise answers, reducing the common problem of LLMs hallucinating or providing incomplete information. It is designed for those who work with structured knowledge bases and need to leverage them for better LLM performance.
No commits in the last 6 months.
Use this if you need to make your large language models more reliable and accurate by grounding their responses in extensive knowledge graphs.
Not ideal if you don't have access to a large knowledge graph like Freebase or are working on simpler natural language processing tasks that don't require external factual verification.
Stars
47
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/SteveTANTAN/PoG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Plale-Lab/patra-knowledge-base
Knowledge Graph to capture AI/ML model lifecycle from creation through deployments.
KGCP/paper2lkg
A Local Knowledge Graph Construction (KGC) pipeline designed to transform individual academic...
ElevenLiy/MAKGED
MAKGED is the first multi-agent framework for collaborative error detection in knowledge graphs.
brandburner/fabula
Turn television drama into storyworld knowledge graphs
zjunlp/xKG
Executable Knowledge Graphs for Replicating AI Research