mlsanityData to 7 Oct 2026

CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning

arXiv 2305.04808 ↗First posted 8 May 2023cs.CLcited by 25

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Commonsense reasoning, aiming at endowing machines with a human-like ability to make situational presumptions, is extremely challenging to generalize. For someone who barely knows about "meditation," while is knowledgeable about "singing," he can still infer that "meditation makes people relaxed" from the existing knowledge that "singing makes people relaxed" by first conceptualizing "singing" as a "relaxing event" and then instantiating that event to "meditation." This process, known as conceptual induction and deduction, is fundamental to commonsense reasoning while lacking both labeled data and methodologies to enhance commonsense modeling. To fill such a research gap, we propose CAT (Contextualized ConceptuAlization and InsTantiation), a semi-supervised learning framework that integrates event conceptualization and instantiation to conceptualize commonsense knowledge bases at scale. Extensive experiments show that our framework achieves state-of-the-art performances on two conceptualization tasks, and the acquired abstract commonsense knowledge can significantly improve commonsense inference modeling. Our code, data, and fine-tuned models are publicly available at https://github.com/HKUST-KnowComp/CAT.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 68 of its 128 references that are in the map. First posted on arXiv 8 May 2023.

Builds on

68 of 128 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023CKBP v2: Better Annotation and Reasoning for Commonsense Knowledge Base Population20 Apr
  2. 2022PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population14 Oct
  3. 2022MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation14 Oct
  4. 2022Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization3 Jun

Other references · 64

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  7. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  10. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  11. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  12. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
38 more
  1. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  2. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  3. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  4. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  5. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  6. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  7. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 486
  8. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  9. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  10. 2020Meta Pseudo Labelscited by 372
  11. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  12. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 330
  13. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 323
  14. 2019Abductive Commonsense Reasoningcited by 300
  15. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  16. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  17. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  18. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  19. 2019WinoGrande: An Adversarial Winograd Schema Challenge at Scalecited by 194
  20. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  21. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 147
  22. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  23. 2019Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Trainingcited by 110
  24. 2022CommonsenseQA 2.0: Exposing the Limits of AI through Gamificationcited by 108
  25. 2019ASER: A Large-scale Eventuality Knowledge Graphcited by 89
  26. 2018Ultra-Fine Entity Typingcited by 87
  27. 2020GLUCOSE: GeneraLized and COntextualized Story Explanationscited by 85
  28. 2019GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledgecited by 78
  29. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  30. 2019Commonsense Knowledge Base Completion with Structural and Semantic Contextcited by 61
  31. 2018Weakly-Supervised Hierarchical Text Classificationcited by 42
  32. 2023Will Affective Computing Emerge from Foundation Models and General AI? A First Evaluation on ChatGPTcited by 41
  33. 2021Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Modelcited by 39
  34. 2023ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relationscited by 39
  35. 2021ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classificationcited by 34
  36. 2021ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualitiescited by 28
  37. 2021Noisy-Labeled NER with Confidence Estimationcited by 28
  38. 2021DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledgecited by 26

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 12; 2025: 5; 2026: 1.

25 papers.

Sort:

By area:

  1. 2024Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extractioncited by 33
  2. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  3. 2023Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraintscited by 21
  4. 2023AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graphcited by 17
  5. 2025Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?cited by 16
  6. 2023Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Modelscited by 11
  7. 2024MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Datasetcited by 11
  8. 2024IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commercecited by 11
  9. 2024MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understandingcited by 10
  10. 2025EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Associationcited by 10
  11. 2024Intention Knowledge Graph Construction for User Intention Relation Modelingcited by 6
  12. 2025arXiv2Table: Toward Realistic Benchmarking and Evaluation for LLM-Based Literature-Review Table Generationcited by 6
13 more
  1. 2025SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understandingcited by 6
  2. 2023QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answeringcited by 4
  3. 2023Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detectioncited by 4
  4. 2026HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learningcited by 4
  5. 2023TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Miningcited by 3
  6. 2024MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discoverycited by 3
  7. 2024On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directionscited by 3
  8. 2024EcomEdit: An Automated E-commerce Knowledge Editing Framework for Enhanced Product and Purchase Intention Understandingcited by 2
  9. 2024What Really is Commonsense Knowledge?cited by 2
  10. 2023Revisiting Sparse Retrieval for Few-shot Entity Linkingcited by 1
  11. 2024Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?cited by 1
  12. 2024EntailE: Introducing Textual Entailment in Commonsense Knowledge Graph Completioncited by 0
  13. 2024Modelling Commonsense Commonalities with Multi-Facet Concept Embeddingscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning
  2. 2025Com2: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models
  3. 2023CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks
  4. 2026Abductive Reasoning with Probabilistic Commonsense
  5. 2022Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach
  6. 2022Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey
  7. 2023UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations
  8. 2022CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm