Journal article
XAI is in trouble
The AI magazine
29 Jul 2024
Abstract
Abstract Researchers focusing on how artificial intelligence (AI) methods explain their decisions often discuss controversies and limitations. Some even assert that most publications offer little to no valuable contributions. In this article, we substantiate the claim that explainable AI (XAI) is in trouble by describing and illustrating four problems: the disagreements on the scope of XAI, the lack of definitional cohesion, precision, and adoption, the issues with motivations for XAI research, and limited and inconsistent evaluations. As we delve into their potential underlying sources, our analysis finds these problems seem to originate from AI researchers succumbing to the pitfalls of interdisciplinarity or from insufficient scientific rigor. Analyzing these potential factors, we discuss the literature at times coming across unexplored research questions. Hoping to alleviate existing problems, we make recommendations on precautions against the challenges of interdisciplinarity and propose directions in support of scientific rigor.
Metrics
3 Record Views
Details
- Title
- XAI is in trouble
- Creators
- Rosina O Weber - Drexel UniversityAdam J Johs - Drexel UniversityPrateek Goel - Drexel UniversityJoão Marques Silva - IRIT CNRS Toulouse France
- Publication Details
- The AI magazine
- Publisher
- AMER ASSOC ARTIFICIAL INTELL; MENLO PK
- Number of pages
- 17
- Grant note
- National Center for Advancing Translational Sciences: 3OT2TR003448-01S1 Biological Technologies Office: DARPA-PA-20-02-06-POCUS-AI-FP-023 Vinnova: 21-03971
National Center for Advancing Translational Sciences, Grant/Award Number: 3OT2TR003448-01S1; Biological Technologies Office, Grant/Award Number:DARPA-PA-20-02-06-POCUS-AI-FP-023; Vinnova, Grant/Award Number: 21-03971
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Information Science (Informatics)
- Identifiers
- 991021895806404721