Position: Explain to Question not to Justify
It addresses the problem of divergent goals in XAI research for AI safety and validation, but it is a position paper with no new methods or results, making it incremental in scope.
The paper identifies a split in Explainable AI (XAI) into human/value-oriented (BLUE XAI) and model/validation-oriented (RED XAI) cultures, arguing that RED XAI is under-explored and needs more methods to question models for safety and improvement.
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.