iText2KG
Incremental knowledge graph construction using LLMs with entity extraction and Neo4j visualization
README
ATOM: AdapTive and OptiMized Dynamic Temporal Knowledge Graph Construction Using LLMs 🎉 Accepted @ EACL 2026 iText2KG is now ATOM. ATOM is a few-shot and scalable approach for building and continuously updating Temporal Knowledge Graphs (TKGs) from unstructured texts. (We kept the legacy iText2KG in the repository, please check the README.) Overview Traditional static KG construction often overlooks the dynamic and time-sensitive nature of real-world data, limiting adaptability to continuous…
- Repository
- github.com/auvalab/itext2kg
Source attribution
- Awesome AI for Science — github.com/auvalab/itext2kg
- GitHub — github.com/auvalab/itext2kg
Related resources
Knowledge graph-guided synthetic data generation for LLM fine-tuning, achieving strong performance on scientific QA (GPQA-Diamond) and math reasoning (AIME)
Structure-aware prefix adaptation for integrating LLMs with knowledge graphs (ACM MM 2024)