mlsanityData to 7 Oct 2026

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

arXiv 2505.23628 ↗First posted 29 May 2025cs.CL cs.AIcited by 23

Not on the map. Why?

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.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 49 of its 84 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

49 of 84 references.

References · 49

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  7. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  9. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  10. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  11. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 475
  12. 2020MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformerscited by 240
37 more
  1. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
  2. 2018WikiHow: A Large Scale Text Summarization Datasetcited by 203
  3. 2023Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?cited by 167
  4. 2019ASER: A Large-scale Eventuality Knowledge Graphcited by 89
  5. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 86
  6. 2023LLM-Rec: Personalized Recommendation via Prompting Large Language Modelscited by 77
  7. 2023LLMs4OL: Large Language Models for Ontology Learningcited by 75
  8. 2024Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Constructioncited by 70
  9. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  10. 2024SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphscited by 31
  11. 2021ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualitiescited by 28
  12. 2023CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answeringcited by 28
  13. 2024CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoningcited by 28
  14. 2023CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoningcited by 25
  15. 2022Query2Particles: Knowledge Graph Reasoning with Particle Embeddingscited by 24
  16. 2022FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discoverycited by 23
  17. 2023DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognitioncited by 23
  18. 2023Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraintscited by 21
  19. 2023Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generationcited by 19
  20. 2024Can LLMs Convert Graphs to Text-Attributed Graphs?cited by 19
  21. 2023Natural Language Decompositions of Implicit Content Enable Better Text Representationscited by 18
  22. 2023AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graphcited by 17
  23. 2020"What Are You Trying to Do?" Semantic Typing of Event Processescited by 16
  24. 2021ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Modelscited by 16
  25. 2023Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Studycited by 14
  26. 2024AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimationcited by 14
  27. 2023Sequential Query Encoding For Complex Query Answering on Knowledge Graphscited by 13
  28. 2025Top Ten Challenges Towards Agentic Neural Graph Databasescited by 13
  29. 2023Knowledge Graph Reasoning over Entities and Numerical Valuescited by 11
  30. 2023Natural Language Decomposition and Interpretation of Complex Utterancescited by 10
  31. 2020Open Knowledge Graphs Canonicalization using Variational Autoencoderscited by 9
  32. 2024Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generationcited by 8
  33. 2024Great Memory, Shallow Reasoning: Limits of kNN-LMscited by 8
  34. 2023Understanding Inter-Session Intentions via Complex Logical Reasoningcited by 7
  35. 2024The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typingcited by 6
  36. 2024Intention Knowledge Graph Construction for User Intention Relation Modelingcited by 6
  37. 2023DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Textcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 13.

23 papers.

Sort:

By area:

  1. 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corporacited by 47
  2. 2025LLM-empowered knowledge graph construction: A surveycited by 20
  3. 2025DeepSieve: Information Sieving via LLM-as-a-Knowledge-Routercited by 13
  4. 2025AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Constructioncited by 6
  5. 2026Ontology-to-tools compilation for executable semantic constraint enforcement in LLM agentscited by 3
  6. 2026NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Trainingcited by 2
  7. 2025TERAG: Token-Efficient Graph-Based Retrieval-Augmented Generationcited by 1
  8. 2025AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAMcited by 1
  9. 2026AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Constructioncited by 1
  10. 2025Robotic Fire Risk Detection based on Dynamic Knowledge Graph Reasoning: An LLM-Driven Approach with Graph Chain-of-Thoughtcited by 0
  11. 2025SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learningcited by 0
  12. 2025OpenGloss: A Synthetic Encyclopedic Dictionary and Semantic Knowledge Graphcited by 0
11 more
  1. 2025InvertiTune: High-Quality Data Synthesis for Cost-Effective Single-Shot Text-to-Knowledge Graph Generationcited by 0
  2. 2026MMKG-RDS: Reasoning Data Synthesis via Deep Mining of Multimodal Knowledge Graphscited by 0
  3. 2026NGDBench: Towards Neural Graph Data Managementcited by 0
  4. 2026Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graph Generationcited by 0
  5. 2026AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generationcited by 0
  6. 2026GenAI-Driven Approach to RISC-V Supply Chain Explorationcited by 0
  7. 2026Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tablescited by 0
  8. 2026JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applicationscited by 0
  9. 2026DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understandingcited by 0
  10. 2026Co-Evolving Structured Knowledge and Reasoning in Language Modelscited by 0
  11. 2026LLMs Interpret, Embeddings Organize, Graphs Emerge: Agent-Driven Compilation of Scientific Knowledgecited by 0