Impact of Legal Requirements on Explainability in Machine Learning
arXiv:2007.05479v110 citations
Originality Synthesis-oriented
AI Analysis
This addresses the problem of legal compliance for ML practitioners and policymakers, but it is incremental as it focuses on interpreting existing laws rather than proposing new solutions.
The research analyzes the unclear explainability requirements imposed by European laws on machine learning models for private and public decision-making, and explores how these obligations can be implemented using ML techniques.
The requirements on explainability imposed by European laws and their implications for machine learning (ML) models are not always clear. In that perspective, our research analyzes explanation obligations imposed for private and public decision-making, and how they can be implemented by machine learning techniques.