mlsanityData to 14 Oct 2026

KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

arXiv 1909.02151 ↗First posted 4 Sep 2019cs.CL cs.AIcited by 216

Not on the map. Why?

Cited by 36 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Commonsense reasoning aims to empower machines with the human ability to make presumptions about ordinary situations in our daily life. In this paper, we propose a textual inference framework for answering commonsense questions, which effectively utilizes external, structured commonsense knowledge graphs to perform explainable inferences. The framework first grounds a question-answer pair from the semantic space to the knowledge-based symbolic space as a schema graph, a related sub-graph of external knowledge graphs. It represents schema graphs with a novel knowledge-aware graph network module named KagNet, and finally scores answers with graph representations. Our model is based on graph convolutional networks and LSTMs, with a hierarchical path-based attention mechanism. The intermediate attention scores make it transparent and interpretable, which thus produce trustworthy inferences. Using ConceptNet as the only external resource for Bert-based models, we achieved state-of-the-art performance on the CommonsenseQA, a large-scale dataset for commonsense reasoning.

Key facts. Cited by 216 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 53; 2022: 58; 2023: 60; 2024: 26; 2025: 12; 2026: 7.

216 papers.

Sort:

By area:

  1. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  2. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 388
  3. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  4. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 233
  5. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  6. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 214
  7. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answeringcited by 171
  8. 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
  9. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  10. 2023Large Language Models as Analogical Reasonerscited by 107
  11. 2022Retrieval Augmented Visual Question Answering with Outside Knowledgecited by 94
  12. 2023Cumulative Reasoning with Large Language Modelscited by 94
38 more
  1. 2023NeurASP: Embracing Neural Networks into Answer Set Programmingcited by 92
  2. 2022MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversationcited by 85
  3. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 80
  4. 2021Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoningcited by 65
  5. 2023Graph Neural Prompting with Large Language Modelscited by 64
  6. 2021RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledgecited by 61
  7. 2024KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoningcited by 60
  8. 2022PINTO: Faithful Language Reasoning Using Prompt-Generated Rationalescited by 56
  9. 2023Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modelingcited by 56
  10. 2024Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsensecited by 51
  11. 2022Knowledge Graph Embedding: A Survey from the Perspective of Representation Spacescited by 41
  12. 2021JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answeringcited by 40
  13. 2021Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attentioncited by 40
  14. 2022Kformer: Knowledge Injection in Transformer Feed-Forward Layerscited by 37
  15. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 35
  16. 2023Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphscited by 35
  17. 2023Graph Reasoning for Question Answering with Triplet Retrievalcited by 34
  18. 2023Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memoriescited by 34
  19. 2021Knowledge Enhanced Pretrained Language Models: A Compreshensive Surveycited by 33
  20. 2021Meta-Knowledge Transfer for Inductive Knowledge Graph Embeddingcited by 32
  21. 2021Conversational Question Answering: A Surveycited by 31
  22. 2023Biomedical knowledge graph-optimized prompt generation for large language modelscited by 31
  23. 2023KnowGPT: Knowledge Graph based Prompting for Large Language Modelscited by 31
  24. 2021Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resourcescited by 30
  25. 2022A Survey of Knowledge-Intensive NLP with Pre-Trained Language Modelscited by 30
  26. 2021Dimensions of Commonsense Knowledgecited by 29
  27. 2023Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentationcited by 29
  28. 2023Pushing the Limits of ChatGPT on NLP Taskscited by 27
  29. 2021"I'm Not Mad": Commonsense Implications of Negation and Contradictioncited by 26
  30. 2021Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledgecited by 24
  31. 2023DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognitioncited by 23
  32. 2021GNN is a Counter? Revisiting GNN for Question Answeringcited by 21
  33. 2021Think about it! Improving defeasible reasoning by first modeling the question scenariocited by 20
  34. 2022VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledgecited by 20
  35. 2024Graph-Based Retriever Captures the Long Tail of Biomedical Knowledgecited by 20
  36. 2021KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generationcited by 19
  37. 2021Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformationcited by 19
  38. 2021Refined Commonsense Knowledge from Large-Scale Web Contentscited by 19

50 most cited of 216 All 216 (JSON)