zjunlp/AutoKG

[WWWJ 2024] LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities

41
/ 100
Emerging

Implements a three-component evaluation framework for LLM-based knowledge graph tasks: zero/one-shot performance benchmarking across entity/relation extraction and event detection (DuIE2.0, SciERC, RE-TACRED, MAVEN), link prediction on reasoning datasets (FB15k-237, ATOMIC2020), and a VINE dataset for assessing virtual knowledge capabilities. The AutoKG system employs multi-agent orchestration built on CAMEL and LangChain, integrating OpenAI APIs and SerpAPI for collaborative KG construction and reasoning tasks.

465 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

465

Forks

41

Language

Python

License

MIT

Last pushed

Jan 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zjunlp/AutoKG"

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