Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution

TL;DR

This paper argues that causality is essential for understanding and resolving trade-offs among fairness, robustness, privacy, and explainability in trustworthy AI, applicable to both classical models and foundation models.

Contribution

It introduces a causality-based framework to interpret and address invariance conflicts in trustworthy AI objectives, offering a unifying perspective.

Findings

Causality helps understand trade-offs as invariance conflicts.

Selective invariance can soften or resolve trade-offs.

Causal assumptions are relevant in large-scale AI systems.

Abstract

As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), is increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously, especially while preserving utility. This position paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI. We ground our arguments in re-interpreting trustworthy AI trade-offs as incompatible invariance requirements under different changes to the data-generating process. We then illustrate that causality provides a unifying framework for understanding how trade-offs in trustworthy AI arise, and how they can be softened or resolved through selective invariance. This perspective applies to both classical ML models and large-scale FMs. Our paper discusses how causal assumptions may be applied explicitly or implicitly in modern large-scale systems. Finally, we outline open challenges and opportunities for using causality to build more trustworthy AI.