mlsanityData to 14 Oct 2026

Symbolic Behaviour in Artificial Intelligence

arXiv 2102.03406 ↗First posted 5 Feb 2021cs.AI cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

The ability to use symbols is the pinnacle of human intelligence, but has yet to be fully replicated in machines. Here we argue that the path towards symbolically fluent artificial intelligence (AI) begins with a reinterpretation of what symbols are, how they come to exist, and how a system behaves when it uses them. We begin by offering an interpretation of symbols as entities whose meaning is established by convention. But crucially, something is a symbol only for those who demonstrably and actively participate in this convention. We then outline how this interpretation thematically unifies the behavioural traits humans exhibit when they use symbols. This motivates our proposal that the field place a greater emphasis on symbolic behaviour rather than particular computational mechanisms inspired by more restrictive interpretations of symbols. Finally, we suggest that AI research explore social and cultural engagement as a tool to develop the cognitive machinery necessary for symbolic behaviour to emerge. This approach will allow for AI to interpret something as symbolic on its own rather than simply manipulate things that are only symbols to human onlookers, and thus will ultimately lead to AI with more human-like symbolic fluency.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 35 of its 145 references that are in the map. First posted on arXiv 5 Feb 2021.

Builds on

35 of 145 references.

References · 35

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  7. 2020Learning to summarize from human feedbackcited by 2,588
  8. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  9. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  10. 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
  11. 2019Solving Rubik's Cube with a Robot Handcited by 734
  12. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
23 more
  1. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 360
  2. 2019Analysing Mathematical Reasoning Abilities of Neural Modelscited by 335
  3. 2019Deep Learning for Symbolic Mathematicscited by 270
  4. 2020Neurosymbolic AI: The 3rd Wavecited by 255
  5. 2018Deep Learning: A Critical Appraisalcited by 217
  6. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 195
  7. 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 170
  8. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 161
  9. 2020A Transformer-based Approach for Source Code Summarizationcited by 133
  10. 2017Grounded Language Learning in a Simulated 3D Worldcited by 100
  11. 2019Neural Machine Translation: A Review and Surveycited by 100
  12. 2019Evaluating Commonsense in Pre-trained Language Modelscited by 95
  13. 2020Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architecturescited by 95
  14. 2020Imitating Interactive Intelligencecited by 55
  15. 2020Grounded Language Learning Fast and Slowcited by 54
  16. 2019Distributional Semantics and Linguistic Theorycited by 53
  17. 2019Environmental drivers of systematicity and generalization in a situated agentcited by 50
  18. 2019Human few-shot learning of compositional instructionscited by 47
  19. 2021LIME: Learning Inductive Bias for Primitives of Mathematical Reasoningcited by 46
  20. 2018Symbol Emergence in Cognitive Developmental Systems: a Surveycited by 39
  21. 2020Meta-learning in natural and artificial intelligencecited by 39
  22. 2019Sample Efficient Text Summarization Using a Single Pre-Trained Transformercited by 27
  23. 2019The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)cited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 7; 2023: 6; 2024: 2; 2025: 2; 2026: 3.

25 papers.

Sort:

By area:

  1. 2022Can language models learn from explanations in context?cited by 249
  2. 2022Language models show human-like content effects on reasoning taskscited by 173
  3. 2022Meaning without reference in large language modelscited by 76
  4. 2023Symbol tuning improves in-context learning in language modelscited by 75
  5. 2021Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learningcited by 40
  6. 2021Tell me why! Explanations support learning relational and causal structurecited by 36
  7. 2023Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning modelscited by 18
  8. 2024SymbolicAI: A framework for logic-based approaches combining generative models and solverscited by 16
  9. 2022Language and Culture Internalisation for Human-Like Autotelic AIcited by 14
  10. 2021Symbol Emergence and The Solutions to Any Taskcited by 9
  11. 2025Whither symbols in the era of advanced neural networks?cited by 7
  12. 2023Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionarycited by 4
13 more
  1. 2025Code-enabled language models can outperform reasoning models on diverse taskscited by 4
  2. 2022Explanatory Learning: Beyond Empiricism in Neural Networkscited by 3
  3. 2022Language Models Understand Us, Poorlycited by 3
  4. 2021Intensional Artificial Intelligence: From Symbol Emergence to Explainable and Empathetic AIcited by 2
  5. 2021Towards Teachable Autotelic Agentscited by 2
  6. 2022Meta-Referential Games to Learn Compositional Learning Behaviourscited by 2
  7. 2026Cognitive Models and AI Algorithms Provide Templates for Designing Language Agentscited by 2
  8. 2023Neuro-Symbolic Execution of Generic Source Codecited by 1
  9. 2023Towards A Unified Neural Architecture for Visual Recognition and Reasoningcited by 1
  10. 2026The Emergent Symbolic Structure of Artificial Neural Networkscited by 1
  11. 2023Glamour muscles: why having a body is not what it means to be embodiedcited by 0
  12. 2024A Moonshot for AI Oracles in the Sciencescited by 0
  13. 2026On Compositional Learning Behaviours in Formal Mathematicscited by 0