Explainable AI needs formalization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Haufe, Stefan, Wilming, Rick, Clark, Benedict, Zhumagambetov, Rustam, Boubekki, Ahcène, Martin, Jörg, Panknin, Danny
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911574724182016
author Haufe, Stefan
Wilming, Rick
Clark, Benedict
Zhumagambetov, Rustam
Boubekki, Ahcène
Martin, Jörg
Panknin, Danny
author_facet Haufe, Stefan
Wilming, Rick
Clark, Benedict
Zhumagambetov, Rustam
Boubekki, Ahcène
Martin, Jörg
Panknin, Danny
contents The field of "explainable artificial intelligence" (XAI) seemingly addresses the desire that decisions of machine learning systems should be human-understandable. However, in its current state, XAI itself needs scrutiny. Popular methods cannot reliably answer relevant questions about ML models, their training data, or test inputs, because they systematically attribute importance to input features that are independent of the prediction target. This limits the utility of XAI for diagnosing and correcting data and models, for scientific discovery, and for identifying intervention targets. The fundamental reason for this is that current XAI methods do not address well-defined problems and are not evaluated against targeted criteria of explanation correctness. Researchers should formally define the problems they intend to solve and design methods accordingly. This will lead to diverse use-case-dependent notions of explanation correctness and objective metrics of explanation performance that can be used to validate XAI algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14590
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Explainable AI needs formalization
Haufe, Stefan
Wilming, Rick
Clark, Benedict
Zhumagambetov, Rustam
Boubekki, Ahcène
Martin, Jörg
Panknin, Danny
Machine Learning
Artificial Intelligence
The field of "explainable artificial intelligence" (XAI) seemingly addresses the desire that decisions of machine learning systems should be human-understandable. However, in its current state, XAI itself needs scrutiny. Popular methods cannot reliably answer relevant questions about ML models, their training data, or test inputs, because they systematically attribute importance to input features that are independent of the prediction target. This limits the utility of XAI for diagnosing and correcting data and models, for scientific discovery, and for identifying intervention targets. The fundamental reason for this is that current XAI methods do not address well-defined problems and are not evaluated against targeted criteria of explanation correctness. Researchers should formally define the problems they intend to solve and design methods accordingly. This will lead to diverse use-case-dependent notions of explanation correctness and objective metrics of explanation performance that can be used to validate XAI algorithms.
title Explainable AI needs formalization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2409.14590