FairnessExplainabilityTrustworthinesscs.AI
A Review of the Role of Causality in Developing Trustworthy AI Systems
Niloy Ganguly, Dren Fazlija, Maryam Badar, Marco Fisichella, Sandipan Sikdar, Johanna Schrader, Jonas Wallat, Koustav Rudra, Manolis Koubarakis, Gourab K. Patro, Wadhah Zai El Amri, Wolfgang Nejdl
February 14, 2023
arXiv.org
33 citations
1 influential
Key Takeaways
-
Current AI models struggle with cause-and-effect reasoning: State-of-the-art AI systems lack understanding of causal relationships that humans naturally use to comprehend the world, which limits their ability to work reliably with new, unseen data.
-
Causality addresses multiple trustworthiness problems simultaneously: Causal methods help tackle interconnected issues including poor generalization to new situations, unfair or biased results, and lack of interpretability—suggesting a unified approach rather than separate fixes for each problem.
-
Causal modeling is emerging as a practical solution: The paper identifies causal modeling and inference methods as "powerful tools" that are being actively developed to improve trustworthiness in AI systems, indicating this is a growing area of research with real-world applications.
-
Trustworthiness requires understanding "why," not just "what": The emphasis on causality suggests that truly trustworthy AI systems need to understand the underlying reasons behind patterns and decisions, not merely recognize correlations in data—a fundamental shift in how AI should be designed.
Abstract
State-of-the-art AI models largely lack an understanding of the cause-effect relationship that governs human understanding of the real world. Consequently, these models do not generalize to unseen data, often produce unfair results, and are difficult to interpret. This has led to efforts to improve the trustworthiness aspects of AI models. Recently, causal modeling and inference methods have emerged as powerful tools. This review aims to provide the reader with an overview of causal methods that have been developed to improve the trustworthiness of AI models. We hope that our contribution will motivate future research on causality-based solutions for trustworthy AI.