mlsanityData to 7 Oct 2026

COMET: Commonsense Transformers for Automatic Knowledge Graph Construction

arXiv 1906.05317 ↗First posted 12 Jun 2019cs.CL cs.AIcited by 450

Not on the map. Why?

Cited by 42 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store knowledge with canonical templates, commonsense KBs only store loosely structured open-text descriptions of knowledge. We posit that an important step toward automatic commonsense completion is the development of generative models of commonsense knowledge, and propose COMmonsEnse Transformers (COMET) that learn to generate rich and diverse commonsense descriptions in natural language. Despite the challenges of commonsense modeling, our investigation reveals promising results when implicit knowledge from deep pre-trained language models is transferred to generate explicit knowledge in commonsense knowledge graphs. Empirical results demonstrate that COMET is able to generate novel knowledge that humans rate as high quality, with up to 77.5% (ATOMIC) and 91.7% (ConceptNet) precision at top 1, which approaches human performance for these resources. Our findings suggest that using generative commonsense models for automatic commonsense KB completion could soon be a plausible alternative to extractive methods.

Key facts. Cited by 450 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 115; 2022: 114; 2023: 106; 2024: 68; 2025: 31; 2026: 16.

450 papers.

Sort:

By area:

  1. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  2. 2022Mass-Editing Memory in a Transformercited by 976
  3. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  4. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  5. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  6. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  7. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  8. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  9. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  10. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
  11. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  12. 2022LinkBERT: Pretraining Language Models with Document Linkscited by 209
38 more
  1. 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 199
  2. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answeringcited by 170
  3. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  4. 2023Large Language Models for Automated Open-domain Scientific Hypotheses Discoverycited by 100
  5. 2021UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmarkcited by 98
  6. 2021CEM: Commonsense-aware Empathetic Response Generationcited by 89
  7. 2022An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labelscited by 88
  8. 2022MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversationcited by 84
  9. 2021Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challengecited by 79
  10. 2022Extracting Cultural Commonsense Knowledge at Scalecited by 76
  11. 2021Understanding by Understanding Not: Modeling Negation in Language Modelscited by 73
  12. 2023Humanoid Agents: Platform for Simulating Human-like Generative Agentscited by 73
  13. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agentscited by 72
  14. 2023Large Language Models and Knowledge Graphs: Opportunities and Challengescited by 71
  15. 2021Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?cited by 62
  16. 2022Housekeep: Tidying Virtual Households using Commonsense Reasoningcited by 57
  17. 2021Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detectioncited by 56
  18. 2021A Systematic Investigation of Commonsense Knowledge in Large Language Modelscited by 56
  19. 2022Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversationcited by 56
  20. 2022PINTO: Faithful Language Reasoning Using Prompt-Generated Rationalescited by 56
  21. 2023Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modelingcited by 56
  22. 2021GooAQ: Open Question Answering with Diverse Answer Typescited by 53
  23. 2024Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?cited by 52
  24. 2024Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsensecited by 50
  25. 2021MERMAID: Metaphor Generation with Symbolism and Discriminative Decodingcited by 49
  26. 2022Generative Knowledge Graph Construction: A Reviewcited by 49
  27. 2022ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classificationcited by 45
  28. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Taskscited by 44
  29. 2023Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversationscited by 41
  30. 2023Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agentscited by 41
  31. 2024CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuningcited by 41
  32. 2021EventBERT: A Pre-Trained Model for Event Correlation Reasoningcited by 40
  33. 2021Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attentioncited by 40
  34. 2022A Decade of Knowledge Graphs in Natural Language Processing: A Surveycited by 40
  35. 2021It's not Rocket Science : Interpreting Figurative Language in Narrativescited by 39
  36. 2021A Survey on Neural-symbolic Learning Systemscited by 39
  37. 2023Instruction-tuning Aligns LLMs to the Human Braincited by 39
  38. 2022Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Surveycited by 38

50 most cited of 450 All 450 (JSON)