# AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora

arXiv: https://arxiv.org/abs/2505.23628 · HTML: https://mlsanity.com/paper/2505.23628/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 84 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 30 of 49)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research](https://mlsanity.com/paper/2402.00159/) (2024)
- [MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers](https://mlsanity.com/paper/2012.15828/) (2020)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [WikiHow: A Large Scale Text Summarization Dataset](https://mlsanity.com/paper/1810.09305/) (2018)
- [Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?](https://mlsanity.com/paper/2308.10168/) (2023)
- [From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2505.13259/) (2025)
- [ASER: A Large-scale Eventuality Knowledge Graph](https://mlsanity.com/paper/1905.00270/) (2019)
- [LLM-Rec: Personalized Recommendation via Prompting Large Language Models](https://mlsanity.com/paper/2307.15780/) (2023)
- [LLMs4OL: Large Language Models for Ontology Learning](https://mlsanity.com/paper/2307.16648/) (2023)
- [Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction](https://mlsanity.com/paper/2404.03868/) (2024)
- [KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation](https://mlsanity.com/paper/2409.13731/) (2024)
- [SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs](https://mlsanity.com/paper/2410.02811/) (2024)
- [ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities](https://mlsanity.com/paper/2104.02137/) (2021)
- [CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering](https://mlsanity.com/paper/2305.14869/) (2023)
- [CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning](https://mlsanity.com/paper/2401.07286/) (2024)
- [CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning](https://mlsanity.com/paper/2305.04808/) (2023)
- [Query2Particles: Knowledge Graph Reasoning with Particle Embeddings](https://mlsanity.com/paper/2204.12847/) (2022)
- [FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery](https://mlsanity.com/paper/2211.08316/) (2022)
- [DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2305.03973/) (2023)
- [Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints](https://mlsanity.com/paper/2305.19068/) (2023)

## Built on by (most cited first, 23 of 23)

- [LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora](https://mlsanity.com/paper/2510.10114/) (2025)
- [LLM-empowered knowledge graph construction: A survey](https://mlsanity.com/paper/2510.20345/) (2025)
- [DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router](https://mlsanity.com/paper/2507.22050/) (2025)
- [AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction](https://mlsanity.com/paper/2510.15339/) (2025)
- [Ontology-to-tools compilation for executable semantic constraint enforcement in LLM agents](https://mlsanity.com/paper/2602.03439/) (2026)
- [TERAG: Token-Efficient Graph-Based Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.18667/) (2025)
- [NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training](https://mlsanity.com/paper/2602.21597/) (2026)
- [AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM](https://mlsanity.com/paper/2510.17934/) (2025)
- [AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction](https://mlsanity.com/paper/2604.16950/) (2026)
- [Robotic Fire Risk Detection based on Dynamic Knowledge Graph Reasoning: An LLM-Driven Approach with Graph Chain-of-Thought](https://mlsanity.com/paper/2509.00054/) (2025)
- [SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning](https://mlsanity.com/paper/2510.01832/) (2025)
- [OpenGloss: A Synthetic Encyclopedic Dictionary and Semantic Knowledge Graph](https://mlsanity.com/paper/2511.18622/) (2025)
- [InvertiTune: High-Quality Data Synthesis for Cost-Effective Single-Shot Text-to-Knowledge Graph Generation](https://mlsanity.com/paper/2512.03197/) (2025)
- [MMKG-RDS: Reasoning Data Synthesis via Deep Mining of Multimodal Knowledge Graphs](https://mlsanity.com/paper/2602.23632/) (2026)
- [NGDBench: Towards Neural Graph Data Management](https://mlsanity.com/paper/2603.05529/) (2026)
- [Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graph Generation](https://mlsanity.com/paper/2604.03496/) (2026)
- [AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation](https://mlsanity.com/paper/2604.09617/) (2026)
- [GenAI-Driven Approach to RISC-V Supply Chain Exploration](https://mlsanity.com/paper/2605.15223/) (2026)
- [Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables](https://mlsanity.com/paper/2605.21974/) (2026)
- [JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications](https://mlsanity.com/paper/2606.28070/) (2026)
- [DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding](https://mlsanity.com/paper/2607.24554/) (2026)
- [Co-Evolving Structured Knowledge and Reasoning in Language Models](https://mlsanity.com/paper/2608.26386/) (2026)
- [LLMs Interpret, Embeddings Organize, Graphs Emerge: Agent-Driven Compilation of Scientific Knowledge](https://mlsanity.com/paper/2608.29612/) (2026)

## Abstract (arXiv)

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.