The Transparency Paradox in Explainable AI: A Theory of Autonomy Depletion Through Cognitive Load

TL;DR

This paper presents a theoretical framework explaining when AI explanations improve or impair human decision-making by modeling cognitive load and autonomy as a stochastic process, leading to adaptive transparency strategies.

Contribution

It introduces a novel stochastic control model of autonomy depletion due to cognitive load, deriving optimal transparency policies that adapt to real-time cognitive states.

Findings

Dynamic transparency policies outperform static ones.

Optimal policies follow a threshold structure based on autonomy and load.

The framework predicts disengagement timing and optimal information levels.

Abstract

Objective: This paper develops a theoretical framework explaining when and why AI explanations enhance versus impair human decision-making. Background: Transparency is advocated as universally beneficial for human-AI interaction, yet identical AI explanations improve decision quality in some contexts but impair it in others. Current theories--trust calibration, cognitive load, and self-determination--cannot fully account for this paradox. Method: The framework models autonomy as a continuous stochastic process influenced by information-induced cognitive load. Using stochastic control theory, autonomy evolution is formalized as geometric Brownian motion with information-dependent drift, and optimal transparency is derived via Hamilton-Jacobi-Bellman equations. Monte Carlo simulations validate theoretical predictions. Results: Mathematical analysis generates five testable predictions about disengagement timing, working memory moderation, autonomy trajectory shapes, and optimal information levels. Computational solutions demonstrate that dynamic transparency policies outperform both maximum and minimum transparency by adapting to real-time cognitive state. The optimal policy exhibits threshold structure: provide information when autonomy is high and accumulated load is low; withhold when resources are depleted. Conclusion: Transparency effects depend on dynamic cognitive resource depletion rather than static design choices. Information provision triggers metacognitive processing that reduces perceived control when cognitive load exceeds working memory capacity. Application: The framework provides design principles for adaptive AI systems: adjust transparency based on real-time cognitive state, implement information budgets respecting capacity limits, and personalize thresholds based on individual working memory capacity.