Supervisory Control Theory for LLM Revision

Abstract

Iterative self-refinement is the dominant paradigm for improving LLM outputs without retraining, yet it lacks principled grounding for what to refine or in what order. We propose Prompt-Level Supervisory Alignment (PLSA), a framework that operationalizes Supervisory Control Theory (SCT), a cognitive framework for human oversight of automated systems, as a structured prompting strategy, and empirically evaluate whether theoretically-grounded prompt structure yields higher revision fidelity than matched iterative self-refinement. In a large-scale evaluation across eight venue-year combinations from three ML conference series (ICLR, NeurIPS, CoRL), SCT-structured conditions produce revisions with significantly higher fidelity to actual author revisions than both a single-pass baseline and a matched two-pass self-refinement baseline that uses identical review information without SCT structure (all $p < .001$, medium-to-large effect sizes). All conditions maintain practically equivalent LLM-judge quality, and cross-model evaluation with Google Gemini 2.5 Flash-Lite corroborates condition rankings, confirming findings are not artifacts of generator self-preference. These results provide empirical evidence that theoretically-grounded prompt structure, not merely iterative refinement, is the operative variable driving higher revision fidelity.