Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces the Multi-Phase Inference Mechanism (MIM), a framework for modeling heterogeneous world models in AI systems. MIM uses phase-formation spaces, foregrounding fields, subject-specific profile states, and alignment maps to formalize how different individuals form distinct representations and inferential targets even from the same observations. The framework reframes world-model alignment as making heterogeneous representations mutually processable, offering a new approach to AI alignment and understanding cognitive diversity.
Forget forcing AI to converge on a single value system – a new framework lets AI understand and work with diverse human worldviews by making differences in meaning visible and transformable.
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.