Position: Explain to Question not to Justify

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Biecek, Przemyslaw, Samek, Wojciech
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914890192519168
author Biecek, Przemyslaw
Samek, Wojciech
author_facet Biecek, Przemyslaw
Samek, Wojciech
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13914
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Position: Explain to Question not to Justify
Biecek, Przemyslaw
Samek, Wojciech
Artificial Intelligence
Cryptography and Security
Machine Learning
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.
title Position: Explain to Question not to Justify
topic Artificial Intelligence
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2402.13914