Intelligence as a Measure of Consciousness
This work addresses the pressing concern of assessing consciousness in AI systems, offering a novel framework that could impact AI ethics and evaluation, though it is incremental in applying existing psychometric concepts to a new domain.
The paper tackles the problem of evaluating consciousness in artificial systems, particularly large language models, by proposing that psychometric measures of intelligence, such as IQ, can approximate the extent of conscious experience based on theories of information coupling.
Evaluating artificial systems for signs of consciousness is increasingly becoming a pressing concern, and a rigorous psychometric measurement framework may be of crucial importance in evaluating large language models in this regard. Most prominent theories of consciousness, both scientific and metaphysical, argue for different kinds of information coupling as a necessary component of human-like consciousness. By comparing information coupling in human and animal brains, human cognitive development, emergent abilities, and mental representation development to analogous phenomena in large language models, I argue that psychometric measures of intelligence, such as the g-factor or IQ, indirectly approximate the extent of conscious experience. Based on a broader source of both scientific and metaphysical theories of consciousness, I argue that all systems possess a degree of consciousness ascertainable psychometrically and that psychometric measures of intelligence may be used to gauge relative similarities of conscious experiences across disparate systems, be they artificial or human.