KG Construction

KG: Knowledge Graph

Ask about this topic

Overview

Knowledge graph construction studies how to turn information from documents, databases, tables, and images into connected, queryable facts. Methods combine named-entity and relation extraction, entity linking and deduplication, and schema or ontology design; newer systems also use large language models and agents, often with expert review and symbolic validation. Provenance, confidence, temporal context, and incremental updates help keep graphs auditable and useful for tasks such as scientific search, clinical reasoning, and question answering. A central challenge is balancing coverage, accuracy, consistency, and construction cost: flexible extraction can capture more information, but schemas, canonicalization, and evidence checks are needed to prevent unsupported or mismatched facts.

Latest papers

CardsList

195 papers20 papers in the last four weeks, up 18% on the four weeks before. 0.1% of all new papers.

  1. Rebuilding a Field's Open-Problem Catalog from the Literature: A Two-Layer Knowledge Graph, and Why Status Must Stay Proposed

    Oct 29, 2026Madhulatha Mandarapu, Sandeep KunkunuruKG ConstructionKnowledge Graph Question Answering

  2. From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion

    Oct 29, 2026Jiaqi Wang, Yisen Gao, Huayang Shi +7KG CompletionLink Prediction

    Tongji University · The Chinese University of Hong Kong · The Hong Kong University of Science and Technology +1

  3. GraphRAGProv: GraphRAG Meets How-Provenance

    Oct 27, 2026Wadie El Amrani, Luis GalárragaGraph Retrieval-Augmented GenerationData Provenance

    Independent Toulouse, France · INRIA Rennes, France

  4. An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warning

    Oct 27, 2026Ngoc Luyen Le, Marie-Hélène Abel, Bertrand LaforgeEarly Warning DetectionDigital Twins

    Gamaizer, 93340 Le Raincy, France · Université de technologie de Compiègne, CNRS, Heudasyc (Heuristics and Diagnosis of Complex Systems), CS 60319, 60203 Compiègne Cedex, France · Sorbonne Université, CNRS UMR 7585, LPNHE (Laboratoire de Physique Nucléaire et des Hautes Énergies), 75252 Paris Cedex 05, France

  5. Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews

    Oct 26, 2026Hari Sitaula, Manish Sakhakarmy, Pujan Pant +1LLM Information ExtractionDocument Information Extraction

    Department of Mathematical Sciences, Montana Technological University, Butte, MT 59701, USA · ASI Industrial, Billings, MT 59101, USA · Herald College Kathmandu, University of Wolverhampton, Naxal, Kathmandu 44600, Nepal

  6. Agreement Between Reconstructed and Native GDELT GKG Records: A Field-Level Baseline

    Oct 26, 2026Nikita A. KliminKG ConstructionDocument Information Extraction

    HSE University, Moscow, Russia

  7. Every Edge Needs a Quote: Building a Quote-Grounded Knowledge Graph of Healthcare Software Adoption with Language-Model Agents

    Oct 23, 2026Juan Felipe Duran, Arthur Tobler, Martin VallièresKG ConstructionRelation Extraction

    Medical Physics Unit, Department of Oncology McGill University, Montreal, Canada · Toboggan Labs Montreal, Canada

  8. Ontology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science Publications

    Oct 23, 2026Aayush Acharya, Qi Zhang, Eduard Dragut +1KG ConstructionOntology-Guided Information Extraction

    Temple University

  9. SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs

    Oct 22, 2026Yifan Yuan, Yancheng Zhu, Zuoyu Zhang +1Knowledge GraphsGrounded Text Generation

    School of Artificial Intelligence, Shenzhen University, Shenzhen, China

  10. Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation

    Oct 21, 2026Yufeng Li, Zaijing Li, Fuchen Zhang +3Graph Retrieval-Augmented GenerationRetrieval-Augmented Reasoning

    Central South University, Changsha, China · Harbin Institute of Technology, Shenzhen, China

  11. Automated Brick Schema Knowledge Graph Completion Across Buildings

    Oct 19, 2026Daniel Ma, Jalil Huseynov, Xinyi Pan +4KG ConstructionKG Completion

    Northeastern University · National University of Singapore · Kajima Corporation

  12. A Semantic Knowledge Graph Construction Pipeline for Vehicle Intention Prediction in nuScenes

    Oct 19, 2026Khaled Nowara, Mohamed Manzour, Catherine EliasKG ConstructionAutonomous Driving

    German University in Cairo, Cairo, Egypt · Computer Engineering Department, University of Alcalá, Madrid, Spain

  13. Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents

    Oct 15, 2026Yutong Leng, Haojiong Chen, Fukai Shang +4Knowledge RepresentationKG Construction

    Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University

  14. MMKG-R1: Constructing Multimodal Knowledge Graphs via Reinforcement Learning

    Oct 14, 2026Zongyu Wu, Yilong Wang, Xiaochen Wang +5KG ConstructionMultimodal KGs

    The Pennsylvania State University

  15. Complex materials engineering via Provenance Action Graphs: potential, structure and demonstration

    Oct 13, 2026Yevgeny Rakita, Paul Todd, James R. Neilson +1Materials DiscoveryMaterials Science

    Department of Materials Engineering, Ben Gurion University of the Negev, Beer-Sheva, Israel · Department of Chemistry, Colorado State University, Fort Collins, CO 80523 · Department Materials, University of California, Santa Barbara, Santa Barbara, CA 93106

  16. Keep Your Receipts: Trustworthy Cleanup of Agent-Built Knowledge Graphs

    Oct 13, 2026Vishisht ChoudharyKnowledge GraphsData Provenance

    Technical University of Munich

  17. Ontology-Based Post-Coordinated Expression Assembly: from Clinical Narrative to Queryable Knowledge Graphs

    Oct 12, 2026Johann Pignat, Christophe Gaudet-Blavignac, Julien Ehrsam +7KG ConstructionClinical Information Extraction

    Service des sciences de l’information médicale, Hôpitaux Universitaires de Genève, Geneva, Switzerland · Service d’oncologie de précision, Hôpitaux Universitaires de Genève, Geneva, Switzerland

  18. Faithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge Graphs

    Oct 8, 2026Haotian Qiao, Robert P. DickKG ConstructionKnowledge Graphs

    Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor, MI, USA

  19. Automatically Building and Updating a Knowledge Graph of MLIP Models

    Oct 7, 2026Alexis Beer, Liudmyla Klochko, Mathieu d'AquinKG Construction

    MosAIk Team, LORIA, Université de Lorraine, CNRS, Nancy, France · CRET AIREL, Université de Lorraine, Nancy, France

  20. Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning

    Oct 6, 2026Ryan C. BarronInformation RetrievalGraph Retrieval-Augmented Generation

  21. Aligning Multimodal Patient Evidence with Biomedical Knowledge Graphs for Clinical LLMs

    Oct 5, 2026Jiawen Du, Arshan Ali Khan, Chenhao Zhang +7KG ConstructionGraph-Based Retrieval

    University of North Carolina at Chapel Hill · Siddaganga Institute of Technology · Foci Labs +1

  22. Agentic schema-guided extraction of materials process knowledge from scientific literature

    Oct 5, 2026Sameer Sadruddin, Jennifer D'SouzaKG ConstructionDocument Information Extraction

    TIB Leibniz Information Centre for Science and Technology, Hannover, Germany.

  23. Curriculum Brain: Constructing Curriculum Knowledge Graphs as a Substrate for Cognitive Diagnosis

    Oct 5, 2026Shrideep Tamboli, Chiranjeevi Maddala, Eshal MinhajKG ConstructionEducational Assessment

    AI Ready School

  24. Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories

    Oct 2, 2026Joseph Chee Chang, Michael D'Arcy, Amy X. Zhang +15Scientific Hypothesis GenerationAI-Assisted Scientific Research

    Allen Institute for AI Seattle, Washington, United States · University of Washington Seattle, Washington, United States · Allen Institute Seattle, Washington, United States +1

  25. LLM-Assisted Discovery of Typed Semantic Links for Ontology Network Construction

    Oct 1, 2026Nouha Hayouni, Sheeba Samuel, Alsayed AlgergawyRelation ExtractionKG Construction

    Chair of Data and Knowledge Engineering, University of Passau, Germany · Distributed and Self-organizing Systems, Chemnitz University of Technology, Germany

  26. 5W1H+Which: Context-Valid Semantic Indexing with Progressive Ontology Binding

    Sep 28, 2026Yaxiao Liu, Pengbo Liu, Yiwen Liu +2KG ConstructionKnowledge Representation

    PwC China AI Center · Tsinghua University

  27. Feedback-Robust AI for Patient Knowledge Graphs

    Sep 27, 2026Mohammed Sameer SyedBiomedical KGsKG Construction

    Roshan AI

  28. ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints

    Sep 24, 2026Sriram Kannan, Swetha Saseendran, Vishnu Vardhan Reddy Kandi +3KG ConstructionDocument Information Extraction

    University of Massachusetts Amherst · Bloomberg

  29. CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding

    Sep 24, 2026Federico Pennino, Andrea Gurioli, Stefano Zacchiroli +2KG ConstructionLLM Information Extraction

    Università di Bologna Bologna, Italy · LTCI Télécom Paris, Institut Polytechnique de Paris Palaiseau, France · DISI Università di Bologna Bologna, Italy +1

  30. Large Knowledge Model: A Knowledge Foundation for Agentic Science at Scale

    Sep 23, 2026Yuan Huang, Sihan Hu, Hongyu Gu +18KG ConstructionAI Agents for Scientific Discovery

    DP Technology, Beijing, China · Institute of Theoretical Physics, Chinese Academy of Sciences, Beijing, China · International Center for Quantum Materials, School of Physics, Peking University, Beijing, China +4