Papers for

ethics compliance teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Framework orders theories and evidence on AI consciousness likelihood

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

Abstract: 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.

Mon 28 SeptArtificial IntelligenceComputers and Society
The gist
The question of whether artificial intelligence can be conscious is complicated by many different and conflicting ideas. The authors create a structured way to look at this question by breaking it into five levels, from behavior to how AI interacts with its environment. They provide ways to measure signs of consciousness at each level and combine these with existing theories to estimate how likely an AI system might be conscious. Their findings show that different assumptions lead to very different conclusions about current AI, like large language models. This approach helps keep discussions clear by making assumptions explicit and treating consciousness likelihood as a probability rather than a simple yes or no.
Open → 2609.35618v1