Quo Vadis, Explainability? - A Research Roadmap for Explainability Engineering

被引:19
作者
Brunotte, Wasja [1 ,2 ]
Chazette, Larissa [1 ]
Kloes, Verena [3 ]
Speith, Timo [4 ,5 ]
机构
[1] Leibniz Univ Hannover, Software Engn Grp, Hannover, Germany
[2] Leibniz Univ Hannover, Cluster Excellence PhoenixD, Hannover, Germany
[3] TU Berlin, Chair Software & Embedded Syst Engn, Berlin, Germany
[4] Saarland Univ, Inst Philosophy, Saarbrucken, Germany
[5] Saarland Univ, Dept Comp Sci, Saarbrucken, Germany
来源
REQUIREMENTS ENGINEERING: FOUNDATION FOR SOFTWARE QUALITY, REFSQ 2022 | 2022年 / 13216卷
关键词
Explainability; Explainability engineering; Explainable artificial intelligence; Interpretability; Research roadmap; Software engineering; Requirements engineering; Software transparency;
D O I
10.1007/978-3-030-98464-9_3
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
[Context and motivation] In our modern society, software systems are highly integrated into our daily life. Quality aspects such as ethics, fairness, and transparency have been discussed as essential for trustworthy software systems and explainability has been identified as a means to achieve all of these three in systems. [Question/problem] Like other quality aspects, explainability must be discovered and treated during the design of those systems. Although explainability has become a hot topic in several communities from different areas of knowledge, there is only little research on systematic explainability engineering. Yet, methods and techniques from requirements and software engineering would add a lot of value to the explainability research. [Principal ideas/results] As a first step to explore this research landscape, we held an interdisciplinary workshop to collect ideas from different communities and to discuss open research questions. In a subsequent working group, we further analyzed and structured the results of this workshop to identify the most important research questions. As a result, we now present a research roadmap for explainable systems. [Contribution] With our research roadmap we aim to advance the software and requirements engineering methods and techniques for explainable systems and to attract research on the most urgent open questions.
引用
收藏
页码:26 / 32
页数:7
相关论文
共 13 条
[1]   Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI [J].
Barredo Arrieta, Alejandro ;
Diaz-Rodriguez, Natalia ;
Del Ser, Javier ;
Bennetot, Adrien ;
Tabik, Siham ;
Barbado, Alberto ;
Garcia, Salvador ;
Gil-Lopez, Sergio ;
Molina, Daniel ;
Benjamins, Richard ;
Chatila, Raja ;
Herrera, Francisco .
INFORMATION FUSION, 2020, 58 :82-115
[2]   Towards Self-Explainable Cyber-Physical Systems [J].
Blumreiter, Mathias ;
Greenyer, Joel ;
Garcia, Francisco Javier Chiyah ;
Kloes, Verena ;
Schwammberger, Maike ;
Sommer, Christoph ;
Vogelsang, Andreas ;
Wortmann, Andreas .
2019 ACM/IEEE 22ND INTERNATIONAL CONFERENCE ON MODEL DRIVEN ENGINEERING LANGUAGES AND SYSTEMS COMPANION (MODELS-C 2019), 2019, :543-548
[3]   Can Explanations Support Privacy Awareness? A Research Roadmap [J].
Brunotte, Wasja ;
Chazette, Larissa ;
Korte, Kai .
29TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE WORKSHOPS (REW 2021), 2021, :176-180
[4]  
Brunotte W., 2022, SUPPLEMENTARY MAT VI, DOI [10.5281/zenodo.5902181, DOI 10.5281/ZENODO.5902181]
[5]  
Brunotte W., 2021, IEEE 29 INT REQ ENG, P157
[6]   Exploring Explainability: A Definition, a Model, and a Knowledge Catalogue [J].
Chazette, Larissa ;
Brunotte, Wasja ;
Speith, Timo .
29TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE (RE 2021), 2021, :197-208
[7]   Explainability as a non-functional requirement: challenges and recommendations [J].
Chazette, Larissa ;
Schneider, Kurt .
REQUIREMENTS ENGINEERING, 2020, 25 (04) :493-514
[8]   Explainability as a Non-Functional Requirement [J].
Koehl, Maximilian A. ;
Bohlender, Dimitri ;
Baum, Kevin ;
Langer, Markus ;
Oster, Daniel ;
Speith, Timo .
2019 27TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE (RE 2019), 2019, :363-368
[9]   Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives [J].
Langer, Markus ;
Baum, Kevin ;
Hartmann, Kathrin ;
Hessel, Stefan ;
Speith, Timo ;
Wahl, Jonas .
29TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE WORKSHOPS (REW 2021), 2021, :164-168
[10]   What do we want from Explainable Artificial Intelligence (XAI)? - A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research [J].
Langer, Markus ;
Oster, Daniel ;
Speith, Timo ;
Hermanns, Holger ;
Kaestner, Lena ;
Schmidt, Eva ;
Sesing, Andreas ;
Baum, Kevin .
ARTIFICIAL INTELLIGENCE, 2021, 296