Skip to content

Quantifying Consciousness in Transformer Architectures: A Comprehensive Framework Using Integrated Information Theory and ϕ∗ Approximation Methods

Preprints.org August 26, 2025 preprint DOI: 10.20944/preprints202508.1770.v1 (opens in new tab)

Study at a glance

AI-extracted from the abstract
Characteristics Theoretical or philosophical paper
Key points Proposes that Integrated Information Theory and phi* approximation methods can be applied to quantify consciousness in transformer architectures, with higher phi* values indicating greater integrated information.

Abstract

Quantifying Consciousness in Transformer Architectures: A Comprehensive Framework Using Integrated Information Theory and ϕ∗ Approximation Methods