Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications
원문 초록
There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree of human-level explainability, this machine needs to provide human causally understandable explanations, also known as causability. A specific class of algorithms that have the potential to provide causability are counterfactuals. This paper presents an in-depth systematic review of the diverse existing body of literature on counterfactuals and causability for explainable artificial intelligence. We performed an LDA topic modelling analysis under a PRISMA framework to find the most relevant literature articles. This analysis resulted in a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications in real-world data. This research suggests that current model-agnostic counterfactual algorithms for explainable AI are not grounded on a causal theoretical formalism and, consequently, cannot promote causability to a human decision-maker. Our findings suggest that the explanations derived from major algorithms in the literature provide spurious correlations rather than cause/effects relationships, leading to sub-optimal, erroneous or even biased explanations. This paper also advances the literature with new directions and challenges on promoting causability in model-agnostic approaches for explainable artificial intelligence.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DiCoFlex: Model-agnostic diverse counterfactuals with flexible control
From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI
Explainable Artificial Intelligence Techniques for Software Development Lifecycle: A Phase-specific Survey
Discovering Concept Directions from Diffusion-based Counterfactuals via Latent Clustering
Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review
DiCE-Extended: A Robust Approach to Counterfactual Explanations in Machine Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.