From cacophony to hierarchy: a principled framework for assessing AI consciousness
This study addresses the challenges of theoretical confounding, limited quantifiability, and the absence of a unified framework in assessing AI consciousness. It proposes a five-level functional descriptive hierarchy grounded in supervenience. Methodologically, by extending Marr’s levels of analysis and integrating coarse-graining with multiple realizability, the work maps mainstream consciousness theories onto this framework, develops operationalizable metrics, and implements structured probabilistic assessment via Bayesian inference. The research advocates shifting metaphysical debates toward "structured agnosticism" and reveals that current consciousness evaluations for large language models are highly sensitive to prior assumptions. Furthermore, it identifies significant overlap between consciousness metrics and architectural features of general intelligence, offering a novel perspective for understanding the evolution of AI capabilities.