We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models to simultaneously extract knowledge triples and induce comprehensive schemas directly from text, modeling both entities and events while employing conceptualization to organize instances into semantic categories. Processing over 50 million documents, we construct ATLAS (Automated Triple Linking And Schema induction), a family of knowledge graphs with 900+ million nodes and 5.9 billion edges. This approach outperforms state-of-the-art baselines on multi-hop QA tasks and enhances LLM factuality. Notably, our schema induction achieves 92\% semantic alignment with human-crafted schemas with zero manual intervention, demonstrating that billion-scale knowledge graphs with dynamically induced schemas can effectively complement parametric knowledge in large language models.
@article{arxiv.2505.23628,
title = {AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora},
author = {Jiaxin Bai and Wei Fan and Qi Hu and Qing Zong and Chunyang Li and Hong Ting Tsang and Hongyu Luo and Yauwai Yim and Haoyu Huang and Xiao Zhou and Feng Qin and Tianshi Zheng and Xi Peng and Xin Yao and Huiwen Yang and Leijie Wu and Yi Ji and Gong Zhang and Renhai Chen and Yangqiu Song},
journal= {arXiv preprint arXiv:2505.23628},
year = {2025}
}