When Does LLM Self-Correction Help? A Control-Theoretic Markov Diagnostic and Verify-First Intervention

This research frames LLM self-correction as a cybernetic feedback loop, using a two-state Markov model to determine when iterative refinement helps versus hurts. It identifies a critical EIR threshold (<= 0.5%) separating beneficial from harmful self-correction, showing that only a few models improve, while others like GPT-5 degrade.