Trustworthiness in Stochastic Systems: Towards Opening the Black Box

2025-01-27

AI Summary

When AI decisions diverge from human expectations, their inherent stochasticity systematically erodes trust; conventional governance paradigms—such as deterministic deployment or user-configurable parameter tuning—fail to support fine-grained trust calibration in high-stakes domains. Method: We introduce *hierarchical stochasticity* as a novel conceptual framework and propose a user-AI co-latent value modeling architecture, integrating philosophical analysis, value-alignment modeling, causal reasoning about trustworthiness, and socio-technical system evaluation. Contribution: We establish a taxonomy-based assessment principle linking stochasticity types to trust impacts, enabling quantifiable measurement of human-AI value alignment. Our approach transcends binary governance (e.g., “on/off” randomness), providing a principled, calibratable foundation for trust regulation in high-risk AI systems. This advances trustworthy AI from empirically driven heuristics toward mechanism-aware, model-based governance.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Humans and AI: Learning Human Values and Preferences
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

AI systems are increasingly tasked to complete responsibilities with decreasing oversight. This delegation requires users to accept certain risks, typically mitigated by perceived or actual alignment of values between humans and AI, leading to confidence that the system will act as intended. However, stochastic behavior by an AI system threatens to undermine alignment and potential trust. In this work, we take a philosophical perspective to the tension and potential conflict between stochasticity and trustworthiness. We demonstrate how stochasticity complicates traditional methods of establishing trust and evaluate two extant approaches to managing it: (1) eliminating user-facing stochasticity to create deterministic experiences, and (2) allowing users to independently control tolerances for stochasticity. We argue that both approaches are insufficient, as not all forms of stochasticity affect trustworthiness in the same way or to the same degree. Instead, we introduce a novel definition of stochasticity and propose latent value modeling for both AI systems and users to better assess alignment. This work lays a foundational step toward understanding how and when stochasticity impacts trustworthiness, enabling more precise trust calibration in complex AI systems, and underscoring the importance of sociotechnical analyses to effectively address these challenges.

Problem

• Artificial Intelligence
• Credibility Assessment
• Human-AI Trust

Innovation

• Randomness Impact
• Potential Value Modeling
• AI Trust Adjustment