mlsanityData to 7 Oct 2026

Consciousness in Artificial Intelligence: Insights from the Science of Consciousness

arXiv 2308.08708 ↗First posted 17 Aug 2023cs.AI cs.CY cs.LGcited by 99

Not on the map. Why?

Abstract (arXiv)

Whether current or near-term AI systems could be conscious is a topic of scientific interest and increasing public concern. This report argues for, and exemplifies, a rigorous and empirically grounded approach to AI consciousness: assessing existing AI systems in detail, in light of our best-supported neuroscientific theories of consciousness. We survey several prominent scientific theories of consciousness, including recurrent processing theory, global workspace theory, higher-order theories, predictive processing, and attention schema theory. From these theories we derive "indicator properties" of consciousness, elucidated in computational terms that allow us to assess AI systems for these properties. We use these indicator properties to assess several recent AI systems, and we discuss how future systems might implement them. Our analysis suggests that no current AI systems are conscious, but also suggests that there are no obvious technical barriers to building AI systems which satisfy these indicators.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). Builds on 43 of its 250 references that are in the map. First posted on arXiv 17 Aug 2023.

Builds on

43 of 250 references.

References · 43

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  6. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  7. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  8. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  9. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  10. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  11. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  12. 2014Recurrent Models of Visual Attentioncited by 344
31 more
  1. 2023Role-Play with Large Language Modelscited by 290
  2. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 273
  3. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 256
  4. 2021Deep learning: a statistical viewpointcited by 239
  5. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  6. 2022Interactive Language: Talking to Robots in Real Timecited by 217
  7. 2016Deep Predictive Coding Networks for Video Prediction and Unsupervised Learningcited by 203
  8. 2018To understand deep learning we need to understand kernel learningcited by 186
  9. 2020A Review on Deep Learning Techniques for Video Predictioncited by 114
  10. 2017The Consciousness Priorcited by 105
  11. 2022Object Scene Representation Transformercited by 90
  12. 2020Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Futurecited by 83
  13. 2021Coordination Among Neural Modules Through a Shared Global Workspacecited by 83
  14. 2023Could a Large Language Model be Conscious?cited by 70
  15. 2022Testing Relational Understanding in Text-Guided Image Generationcited by 59
  16. 2019Recurrence is required to capture the representational dynamics of the human visual systemcited by 58
  17. 2020Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systemscited by 48
  18. 2022Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?cited by 45
  19. 2023GFlowNet-EM for learning compositional latent variable modelscited by 40
  20. 2020Deep Learning and the Global Workspace Theorycited by 35
  21. 2019Deep neuroethology of a virtual rodentcited by 22
  22. 2020Learning to Fly via Deep Model-Based Reinforcement Learningcited by 19
  23. 2023The feasibility of artificial consciousness through the lens of neurosciencecited by 18
  24. 2021Predictive coding feedback results in perceived illusory contours in a recurrent neural networkcited by 10
  25. 2019Awareness as inference in a higher-order state spacecited by 7
  26. 2019Controversial stimuli: pitting neural networks against each other as models of human recognitioncited by 7
  27. 2023Sources of Richness and Ineffability for Phenomenally Conscious Statescited by 7
  28. 2021Neural optimal feedback control with local learning rulescited by 5
  29. 2023Attention Schema in Neural Agentscited by 4
  30. 2020Multimodal Data Fusion based on the Global Workspace Theorycited by 3
  31. 2021What we are is more than what we docited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 24; 2025: 29; 2026: 38.

99 papers.

Sort:

By area:

  1. 2025LLM Social Simulations Are a Promising Research Methodcited by 97
  2. 2023Levels of AGI for Operationalizing Progress on the Path to AGIcited by 94
  3. 2023Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoningcited by 49
  4. 2024How Far Are We From AGI: Are LLMs All We Need?cited by 31
  5. 2024Artificial General Intelligence (AGI)-Native Wireless Systems: A Journey Beyond 6Gcited by 30
  6. 2024Taking AI Welfare Seriouslycited by 28
  7. 2025Does It Make Sense to Speak of Introspection in Large Language Models?cited by 22
  8. 2023Towards Evaluating AI Systems for Moral Status Using Self-Reportscited by 21
  9. 2024A Philosophical Introduction to Language Models - Part II: The Way Forwardcited by 17
  10. 2024Simulacra as Conscious Exoticacited by 16
  11. 2024Can LLMs make trade-offs involving stipulated pain and pleasure states?cited by 16
  12. 2025Large Language Models Report Subjective Experience Under Self-Referential Processingcited by 16
38 more
  1. 2024From Imitation to Introspection: Probing Self-Consciousness in Language Modelscited by 14
  2. 2024Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMscited by 11
  3. 2024Is artificial consciousness achievable? Lessons from the human braincited by 11
  4. 2025Evidence for Limited Metacognition in LLMscited by 11
  5. 2026Can LLMs Introspect? A Reality Checkcited by 8
  6. 2024A Case for AI Consciousness: Language Agents and Global Workspace Theorycited by 7
  7. 2024Dissociating Artificial Intelligence from Artificial Consciousnesscited by 7
  8. 2025Know Thyself? On the Incapability and Implications of AI Self-Recognitioncited by 7
  9. 2024Agnosticism About Artificial Consciousnesscited by 6
  10. 2025Principles for Responsible AI Consciousness Researchcited by 6
  11. 2024Integration of cognitive tasks into artificial general intelligence test for large modelscited by 5
  12. 2025Analyzing the Ethical Logic of Eight Large Language Modelscited by 5
  13. 2025Palatable Conceptions of Disembodied Beingcited by 5
  14. 2026Positive Alignment: Artificial Intelligence for Human Flourishingcited by 5
  15. 2023User-Like Bots for Cognitive Automation: A Surveycited by 4
  16. 2023A Turing Test: Are AI Chatbots Behaviorally Similar to Humans?cited by 4
  17. 2024Preliminaries to artificial consciousness: a multidimensional heuristic approachcited by 4
  18. 2024Recognizing Limits: Investigating Infeasibility in Large Language Modelscited by 4
  19. 2025Emergence of psychopathological computations in large language modelscited by 4
  20. 2023Survey of Consciousness Theory from Computational Perspectivecited by 3
  21. 2024Synergising Human-like Responses and Machine Intelligence for Planning in Disaster Responsecited by 3
  22. 2025Identifying Features that Shape Perceived Consciousness in Large Language Model-based AI: A Quantitative Study of Human Responsescited by 3
  23. 2025What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patternscited by 3
  24. 2026No Reliable Evidence of Self-Reported Sentience in Small Large Language Modelscited by 3
  25. 2026Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Modelscited by 3
  26. 2026Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?cited by 3
  27. 2024Position Paper: Agent AI Towards a Holistic Intelligencecited by 2
  28. 2025AI Generations: From AI 1.0 to AI 4.0cited by 2
  29. 2025The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approachcited by 2
  30. 2025Extreme Self-Preference in Language Modelscited by 2
  31. 2025Hey Pentti, We Did It!: A Fully Vector-Symbolic Lispcited by 2
  32. 2025A Disproof of Large Language Model Consciousness: The Necessity of Continual Learning for Consciousnesscited by 2
  33. 2026Post-AGI Economies: Autonomy and the First Fundamental Theorem of Welfare Economicscited by 2
  34. 2026Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Modelscited by 2
  35. 2026Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvementcited by 2
  36. 2024Can AI and humans genuinely communicate?cited by 1
  37. 2024Can a Machine be Conscious? Towards Universal Criteria for Machine Consciousnesscited by 1
  38. 2024Report on Candidate Computational Indicators for Conscious Valenced Experiencecited by 1

50 most cited of 99 All 99 (JSON)