AI RESEARCH
Towards Effective Theory of LLMs: A Representation Learning Approach
arXiv CS.AI
•
ArXi:2605.09294v1 Announce Type: cross We propose Representational Effective Theory (RET), a framework for describing large language model computation in terms of learned macrostates rather than microscopic details. RET learns these macrostates from hidden-state trajectories using a BYOL/JEPA-style self-supervised objective, coarse-graining activations into macrovariables that preserve higher-level structure relevant for prediction and interpretation.