Position: Explain to Question not to Justify

TL;DR

This paper advocates for a shift in XAI research focus towards model/validation-oriented explanations (RED XAI), emphasizing its importance for AI safety and the need for new methods to interrogate and improve models.

Contribution

It introduces the distinction between human/value-oriented and model/validation-oriented explanations, highlighting the under-explored potential of RED XAI for AI safety and model improvement.

Findings

RED XAI is under-explored and crucial for AI safety.

More methods are needed to interrogate and fix models.

Opportunities exist for significant research in RED XAI.

Abstract

Explainable Artificial Intelligence (XAI) is a young but very promising field of research. Unfortunately, the progress in this field is currently slowed down by divergent and incompatible goals. We separate various threads tangled within the area of XAI into two complementary cultures of human/value-oriented explanations (BLUE XAI) and model/validation-oriented explanations (RED XAI). This position paper argues that the area of RED XAI is currently under-explored, i.e., more methods for explainability are desperately needed to question models (e.g., extract knowledge from well-performing models as well as spotting and fixing bugs in faulty models), and the area of RED XAI hides great opportunities and potential for important research necessary to ensure the safety of AI systems. We conclude this paper by presenting promising challenges in this area.