Toward AI Systems That Understand Self and Others: A Multi-Phase Inference Framework for Human Cognitive Diversity and World-Model Alignment
For AI alignment and social cognition, it provides a vocabulary to address mutual misunderstanding by modeling cognitive diversity, but remains theoretical without empirical validation.
The paper proposes a multi-phase inference framework (MIM) to formalize how heterogeneous world models arise from the same observations, reframing alignment as making diverse representations mutually processable rather than convergent.
Mutual misunderstanding in contemporary society does not arise merely because people hold different opinions or values. Even under the same observations, different subjects may form different inferential targets, state representations, prediction errors, and update priorities. This paper proposes a multi-phase inference framework and defines its core internal mechanism as the Multi-Phase Inference Mechanism (MIM). MIM formalizes how heterogeneous world models arise through a phase-formation space, a foregrounding field, subject-specific profile states, and alignment maps between state representations. On this basis, the paper reframes world-model alignment as the problem of making heterogeneous representations mutually processable, rather than forcing agreement or convergence to a single value system. It further connects this formalism to philosophical disagreements, cognitive typology, social fragmentation, and AI alignment. The aim is to provide a constructive vocabulary for AI systems that can help humans understand self and others by making differences in meaning, value, and prediction error visible, comparable, and transformable.