mlsanityData to 7 Oct 2026

Abstraction and Analogy-Making in Artificial Intelligence

arXiv 2102.10717 ↗First posted 22 Feb 2021cs.AIcited by 103

Not on the map. Why?

Cited by 38 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite of a long history of research on constructing AI systems with these abilities, no current AI system is anywhere close to a capability of forming humanlike abstractions or analogies. This paper reviews the advantages and limitations of several approaches toward this goal, including symbolic methods, deep learning, and probabilistic program induction. The paper concludes with several proposals for designing challenge tasks and evaluation measures in order to make quantifiable and generalizable progress in this area.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). Builds on 42 of its 123 references that are in the map. First posted on arXiv 22 Feb 2021.

Builds on

42 of 123 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  7. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  8. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
  9. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  10. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
  11. 2017A simple neural network module for relational reasoningcited by 345
  12. 2019RAVEN: A Dataset for Relational and Analogical Visual rEasoNingcited by 225
30 more
  1. 2018Measuring abstract reasoning in neural networkscited by 165
  2. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 159
  3. 2018Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objectscited by 143
  4. 2020How Can We Accelerate Progress Towards Human-like Linguistic Generalization?cited by 114
  5. 2017Learning to Infer Graphics Programs from Hand-Drawn Imagescited by 73
  6. 2018Synthesizing Programs for Images using Reinforced Adversarial Learningcited by 72
  7. 2020Stratified Rule-Aware Network for Abstract Visual Reasoningcited by 72
  8. 2020Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoningcited by 63
  9. 2019Learning Perceptual Inference by Contrastingcited by 57
  10. 2020Grounded Language Learning Fast and Slowcited by 54
  11. 2019Learning to Make Analogies by Contrasting Abstract Relational Structurecited by 53
  12. 2019Environmental drivers of systematicity and generalization in a situated agentcited by 50
  13. 2020Emergent Symbols through Binding in External Memorycited by 47
  14. 2020The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoningcited by 46
  15. 2020Meta-learning in natural and artificial intelligencecited by 39
  16. 2020Learning Representations that Support Extrapolationcited by 36
  17. 2019Abstract Reasoning with Distracting Featurescited by 33
  18. 2019Making sense of sensory inputcited by 29
  19. 2018Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representationscited by 28
  20. 2018Solving Bongard Problems with a Visual Language and Pragmatic Reasoningcited by 21
  21. 2018Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programscited by 21
  22. 2015VISALOGY: Answering Visual Analogy Questionscited by 17
  23. 2020Solving Raven's Progressive Matrices with Multi-Layer Relation Networkscited by 16
  24. 2019Attention on Abstract Visual Reasoningcited by 15
  25. 2020Learning Task-General Representations with Generative Neuro-Symbolic Modelingcited by 14
  26. 2020Solving Raven's Progressive Matrices with Neural Networkscited by 13
  27. 2020Generating new concepts with hybrid neuro-symbolic modelscited by 9
  28. 2020Neural Analogical Matchingcited by 7
  29. 2017Semantic Image Retrieval via Active Grounding of Visual Situationscited by 4
  30. 2020We Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videoscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 22; 2023: 28; 2024: 21; 2025: 16; 2026: 8.

103 papers.

Sort:

By area:

  1. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  2. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRscited by 373
  3. 2022Emergent Analogical Reasoning in Large Language Modelscited by 239
  4. 2022Language models show human-like content effects on reasoning taskscited by 171
  5. 2023The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domaincited by 97
  6. 2022A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matricescited by 64
  7. 2022Putting GPT-3's Creativity to the (Alternative Uses) Testcited by 62
  8. 2023Collaborating with language models for embodied reasoningcited by 61
  9. 2021Why AI is Harder Than We Thinkcited by 40
  10. 2022Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matricescited by 37
  11. 2022Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge networkcited by 34
  12. 2021Fast and flexible: Human program induction in abstract reasoning taskscited by 33
38 more
  1. 2022A Review of Emerging Research Directions in Abstract Visual Reasoningcited by 33
  2. 2023FIND: A Function Description Benchmark for Evaluating Interpretability Methodscited by 32
  3. 2024MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learningcited by 30
  4. 2023Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matchingcited by 29
  5. 2022Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPTcited by 27
  6. 2022Are Deep Neural Networks SMARTer than Second Graders?cited by 24
  7. 2023IRFL: Image Recognition of Figurative Languagecited by 23
  8. 2022Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processescited by 22
  9. 2022VASR: Visual Analogies of Situation Recognitioncited by 22
  10. 2023In-Context Analogical Reasoning with Pre-Trained Language Modelscited by 22
  11. 2024KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Modelscited by 22
  12. 2023Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributionscited by 21
  13. 2022WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Modelscited by 20
  14. 2022Abstraction for Deep Reinforcement Learningcited by 19
  15. 2023Learning to Extrapolate: A Transductive Approachcited by 19
  16. 2024LLMs as Models for Analogical Reasoningcited by 16
  17. 2024MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMscited by 15
  18. 2021Probabilistic Analogical Mapping with Semantic Relation Networkscited by 14
  19. 2022Gathering Strength, Gathering Storms: The One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Reportcited by 14
  20. 2023Do large language models solve verbal analogies like children do?cited by 13
  21. 2023Evaluating the Deductive Competence of Large Language Modelscited by 12
  22. 2023Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abductioncited by 11
  23. 2023AI for Mathematics: A Cognitive Science Perspectivecited by 10
  24. 2024AI-enhanced Collective Intelligencecited by 10
  25. 2023Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matricescited by 9
  26. 2024Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architecturescited by 9
  27. 2024Towards Learning Abductive Reasoning using VSA Distributed Representationscited by 9
  28. 2024Can Large Language Models generalize analogy solving like children can?cited by 9
  29. 2022Zero-shot visual reasoning through probabilistic analogical mappingcited by 8
  30. 2023ARN: Analogical Reasoning on Narrativescited by 8
  31. 2023Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized methodcited by 8
  32. 2024ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogiescited by 8
  33. 2023Graph schemas as abstractions for transfer learning, inference, and planningcited by 7
  34. 2024Do Large Language Models Solve ARC Visual Analogies Like People Do?cited by 7
  35. 2024Creativity in AI: Progresses and Challengescited by 7
  36. 2025Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problemscited by 7
  37. 2025Measuring Combinatorial Creativity in Large Language Models and Humanscited by 7
  38. 2021A Neural Approach for Detecting Morphological Analogiescited by 6

50 most cited of 103 All 103 (JSON)