mlsanityData to 14 Oct 2026

Generations of Knowledge Graphs: The Crazy Ideas and the Business Impact

arXiv 2308.14217 ↗First posted 27 Aug 2023cs.DB cs.AI cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Knowledge Graphs (KGs) have been used to support a wide range of applications, from web search to personal assistant. In this paper, we describe three generations of knowledge graphs: entity-based KGs, which have been supporting general search and question answering (e.g., at Google and Bing); text-rich KGs, which have been supporting search and recommendations for products, bio-informatics, etc. (e.g., at Amazon and Alibaba); and the emerging integration of KGs and LLMs, which we call dual neural KGs. We describe the characteristics of each generation of KGs, the crazy ideas behind the scenes in constructing such KGs, and the techniques developed over time to enable industry impact. In addition, we use KGs as examples to demonstrate a recipe to evolve research ideas from innovations to production practice, and then to the next level of innovations, to advance both science and business.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 20 of its 50 references that are in the map. First posted on arXiv 27 Aug 2023.

Builds on

20 of 50 references.

References · 20

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  3. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  4. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  5. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 319
  6. 2020KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoningcited by 106
  7. 2018OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]cited by 63
  8. 2021AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decodingcited by 32
  9. 2020AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Typescited by 31
  10. 2020ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpagescited by 30
  11. 2020TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categoriescited by 29
  12. 2020Octet: Online Catalog Taxonomy Enrichment with Self-Supervisioncited by 22
8 more
  1. 2015Knowledge-Based Trust: Estimating the Trustworthiness of Web Sourcescited by 21
  2. 2021PAM: Understanding Product Images in Cross Product Category Attribute Extractioncited by 18
  3. 2018CERES: Distantly Supervised Relation Extraction from the Semi-Structured Webcited by 11
  4. 2015From Data Fusion to Knowledge Fusioncited by 10
  5. 2021End-to-End Conversational Search for Online Shopping with Utterance Transfercited by 7
  6. 2021Deep Transfer Learning for Multi-source Entity Linkage via Domain Adaptationcited by 7
  7. 2022PGE: Robust Product Graph Embedding Learning for Error Detectioncited by 5
  8. 2015Scaling up Copy Detectioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 2; 2026: 2.

10 papers.

  1. 2024Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Surveycited by 53
  2. 2024Uncertainty Management in the Construction of Knowledge Graphs: a Surveycited by 5
  3. 2023Trust, Accountability, and Autonomy in Knowledge Graph-based AI for Self-determinationcited by 2
  4. 2024Context Graphcited by 2
  5. 2024Interactive Ontology Matching with Cost-Efficient Learningcited by 1
  6. 2024Semantic Web: Past, Present, and Future (with Machine Learning on Knowledge Graphs and Language Models on Knowledge Graphs)cited by 0
  7. 2025ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sourcescited by 0
  8. 2025Leveraging LLMs to Create Content Corpora for Niche Domainscited by 0
  9. 2026Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answeringcited by 0
  10. 2026Ontology-Driven Structural Regularization for Document-Level Relation Extractioncited by 0