Han, Huiwen: Semantic Entropy and Structural Invariance in LLM-Mediated ExpansionCompression Loops
We develop a quantitative information-theoretic account of semantic decay in large-
language-model (LLM) mediated ExpansionCompression (EC) loops. Building on
the unied framework of DECO Paper 0 (Han, 2026a), we introduce semantic en-
tropy HS(X) as the dierential entropy of a random variable distributed over a
semantic manifold, and prove that each application of the EC-transform T = C ◦ E
is a strictly entropy-reducing operation in expectation (Semantic Entropy Collapse
Theorem). We derive clo
