What Can Analogy Tell Us About Artificial Consciousness?

Keith J. Holyoak; Martin M. Monti

cs.AIOct 1, 2026

What Can Analogy Tell Us About Artificial Consciousness?

Authors: Keith J. Holyoak, Martin M. Monti

Organizations: Department of Psychology, University of California, Los Angeles · Brain Injury Research Center, Department of Neurosurgery, University of California, Los Angeles

Abstract

Who or what is conscious? Because subjective experience is directly accessible only in the first person, judgments about consciousness in other entities depend partly on analogy. Historically, such inferences have focused on nonhuman animals, but advances in artificial intelligence have raised the possibility of conscious AI. Here we develop a causal framework for evaluating such evidential analogies. The key distinction is between similarities in factors plausibly involved in generating consciousness and similarities in downstream behavioural or cognitive effects. Our framework weights source-target similarity by causal relevance while allowing for unknown causes, disabling differences and alternative routes to consciousness. Applied to biological systems, it explains why analogical support generally weakens with increasing causal distance from humans. Applied to contemporary AI, it suggests that behavioural similarity provides only limited evidence for consciousness because relevant causal correspondences remain poorly established. The framework also clarifies what evidence would strengthen claims of artificial consciousness.

Figures & tables

Figure 1: A causal approach to evidential analogy for consciousness. Human consciousness provides the principal source analogue for evaluating consciousness in other systems. The framework distinguishes candidate causal features of consciousness from observable behavioural and cognitive outcomes, because similarity in downstream effects does not by itself establish similarity in the mechanisms that generate consciousness. The strength of an evidential analogy depends on the extent to which a target shares factors that are plausibly causally relevant, while also considering unknown causes, potential disablers and the possibility of alternative mechanisms. The right panel provides a qualitative, schematic comparison of different target systems; the categories are illustrative and not quantitative estimates.

Explore similar work

From cacophony to hierarchy: a principled framework for assessing AI consciousness
Sep 28, 2026Shamil Chandaria, Arvo Muñoz Morán, Fernando Rosas +11Possibilities Hierarchical
Google DeepMind, DeepMind Institute · Flourishing Intelligence Program, Centre for Eudaimonia and Human Flourishing, Linacre College, University of Oxford · Institute of Philosophy, University of London +14
When Should We Protect AI? A Precautionary Framework for Consciousness Uncertainty
Jun 4, 2026Anna MikedaEthics Moral Reasoning
Glass Umbrella
Intrinsic Computational Functionalism and Simulated Consciousness
Jun 13, 2026Ryota Kanai, Shuqin Ma
Araya Inc., Tokyo, Japan · School of Philosophy, Fudan University, Shanghai, China · Sussex Centre for Consciousness Science, University of Sussex, Brighton, UK

Sep 28, 2026, cs.AIJ/K move · Enter open · S save

From cacophony to hierarchy: a principled framework for assessing AI consciousness

Shamil Chandaria, Arvo Muñoz Morán, Fernando Rosas, Anil Seth+10

Google DeepMind, DeepMind Institute · Flourishing Intelligence Program, Centre for Eudaimonia and Human Flourishing, Linacre College, University of Oxford · Institute of Philosophy, University of London+14

Possibilities Hierarchical

Open paper AskPDF arXiv

The question of AI consciousness is one of the most urgent pre-emptive problems in philosophy and computer science, yet progress is hampered by a cacophony of competing theories that often talk past each other. Separating the hard problem from the mapping problem allows the deepest metaphysical disagreements to be set aside: granting that experience supervenes on a system's organisation, the tractable question becomes at which grain of description that supervenience base sits. We extend Marr's three levels of analysis into a five-level hierarchy of functional descriptions (behavioural, computational, intrinsic causal-structural, organismic, and organism-environment) grounded in supervenience, coarse-graining, and multiple realisability. The major theories of consciousness are positioned within this hierarchy according to which level they take to be critical, and for each level we develop operationalisable indicators and assess current AI systems against them. A Bayesian model then combines theoretical credences with indicator evidence into an overall credence in a system's capacity for consciousness. In illustrative assessments, the verdict for current LLMs is driven as much by where theoretical credence is placed as by how the evidence is read: under different stipulated readings and credence distributions, assessments range from below 0.01 to roughly 0.8, showing sensitivity to assumptions. Finally, the consciousness indicators at each level closely overlap with the architectural features needed for general intelligence, suggesting that increasingly capable AI may become a stronger candidate for consciousness. The framework supports a structured agnosticism, in which theoretical commitments are made explicit, credences are updated as evidence accumulates, and assessments take the form of aggregated probabilities rather than verdicts.

Abstract

Explore similar work

From cacophony to hierarchy: a principled framework for assessing AI consciousness

When Should We Protect AI? A Precautionary Framework for Consciousness Uncertainty

Intrinsic Computational Functionalism and Simulated Consciousness