Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation

By Jichen Zhu, Antonios Liapis, Sebastian Risi, Rafael Bidarra, G. Youngblood. 2018

240 citations recorded by the source corpus.

Growing interest in eXplainable Artificial Intelligence (XAI) aims to make AI and machine learning more understandable to human users. However, most existing work focuses on new algorithms, and not on usability, practical interpretability and efficacy on real users. In this vision paper, we propose a new research area of eXplainable AI for Designers (XAID), specifically for game designers. By focusing on a specific user group, their needs and tasks, we propose a human-centered approach for facilitating game designers to co-create with AI/ML techniques through XAID. We illustrate our initial XAID framework through three use cases, which require an understanding both of the innate properties of the AI techniques and users’ needs, and we identify key open challenges.

Subfields: Artificial Intelligence, Health Informatics, Safety Research, Safety, Robustness & Interpretability, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Informatics

In Safety Research

In Safety, Robustness & Interpretability

In Human-Computer Interaction

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “In general, humans are reticent to adopt techniques that are not directly interpretable, tractable and trustworthy [9] , given the increasing demand for ethical AI [3] .”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “[157] noted that most existing works focus on new explainingmethods, and not on usability, practical interpretability and efficacy on real users.”
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence (2023, background): “Zhu et al. [88] noticed that instead of focusing on the practicality and efficacy of current XAI practices, most works are coming up with new methods of explanations.”
Questioning the AI: Informing Design Practices for Explainable AI User Experiences (2020, background): “Future work could study other roles involved in AI product development (e.g., data scientists) to better understand the challenges to create XAI products.”
Interpreting Interpretability: Understanding Data Scientists' Use of Interpretability Tools for Machine Learning (2020, background): “[60] provide domain specific results for challenges of designing iML systems for software developers and game designers, respectively.”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, unknown): “gn, Eiband et al. [56] present a stage-based participatory process for integration of transparency in existing intelligent systems using explanations. Another design framework is XAID from Zhu et al. [225], which presents a human-centered approach for facilitating game designers to co-create with ma”
Sequential Explanations with Mental Model-Based Policies (2020, background): “…2018; Madumal et al., 2019) and explainee’s local simulatability of the black-box model for each classiﬁcation possibility (Hoffman et al., 2018; Doshi-Velez & Kim, 2017; Lipton, 2016; Kim et al., 2016; Gilpin et al., 2018; Madumal et al., 2019; Poursabzi-Sangdeh et al., 2018; Zhu et al., 2018).”
Explanations in Autonomous Driving: A Survey (2021, background): “Second, researchers suggested (in [77]) that understanding users’ requirements might be helpful in explainable AI research.”
Towards Explainable Neural-Symbolic Visual Reasoning (2019, background): “Some common cases are a need for ethics [Goodman and Flaxman, 2017], for safety when using AI in high-risk environments [Caruana et al., 2015] or a need to allow the final user to trust the system [Zhu et al., 2018].”