How to Choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice

Vermeire, Tom; Laugel, Thibault; Renard, Xavier; Martens, David; Detyniecki, Marcin

doi:10.1007/978-3-030-93736-2_39

Cited by 7 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many articles have provided rosters of different types of explanations, framed as either a taxonomy of types or a classification based on multiple qualitative dimensions (e.g., Floridi et al, 2018;Sheh and Monteath, 2018;Hind et al, 2019;Arrieta et al, 2020;Dahan, 2020;Vermeire et al, 2021). Also, many articles refer to particular domains such as Health Care, Data Analytics, AI, and Verification and Validation (Preece et al, 2018;Arya et al, 2019;Chari et al, 2020;Mohseni et al, 2020) or legal domains (Al-Abdulkarim et al, 2016;Al-Abdulakarim et al, 2019;Felzmann et al, 2019;Atkinson et al, 2020).…”

Section: Types Of Explanationsmentioning

confidence: 99%

Explainable AI: roles and stakeholders, desirements and challenges

Hoffman,

Mueller,

Klein

et al. 2023

Front. Comput. Sci.

View full text Add to dashboard Cite

IntroductionThe purpose of the Stakeholder Playbook is to enable the developers of explainable AI systems to take into account the different ways in which different stakeholders or role-holders need to “look inside” the AI/XAI systems.MethodWe conducted structured cognitive interviews with senior and mid-career professionals who had direct experience either developing or using AI and/or autonomous systems.ResultsThe results show that role-holders need access to others (e.g., trusted engineers and trusted vendors) for them to be able to develop satisfying mental models of AI systems. They need to know how it fails and misleads as much as they need to know how it works. Some stakeholders need to develop an understanding that enables them to explain the AI to someone else and not just satisfy their own sense-making requirements. Only about half of our interviewees said they always wanted explanations or even needed better explanations than the ones that were provided. Based on our empirical evidence, we created a “Playbook” that lists explanation desires, explanation challenges, and explanation cautions for a variety of stakeholder groups and roles.DiscussionThis and other findings seem surprising, if not paradoxical, but they can be resolved by acknowledging that different role-holders have differing skill sets and have different sense-making desires. Individuals often serve in multiple roles and, therefore, can have different immediate goals. The goal of the Playbook is to help XAI developers by guiding the development process and creating explanations that support the different roles.

show abstract

Section: Types Of Explanationsmentioning

confidence: 99%

Explainable AI: roles and stakeholders, desirements and challenges

Hoffman,

Mueller,

Klein

et al. 2023

Front. Comput. Sci.

View full text Add to dashboard Cite

show abstract

“…Eventually, [16] highlights that users should be guided in choosing XAI solutions and proposes a methodology for this issue, while [17] proposes a theoretical framework to facilitate the comparison between XAI solutions.…”

Section: Approaches For Choosing An Xai Solutionmentioning

confidence: 99%

“…These are tedious and time-consuming tasks. Theoretical guides have been proposed by [16,17] but, to the best of our knowledge, automating the complete XAI recommendation approach has never been formalized and implemented before.…”

Section: Introductionmentioning

confidence: 99%

AutoXAI

Cugny

Aligon

Chevalier

et al. 2022

Proceedings of the 31st ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

A large number of XAI (eXplainable Artificial Intelligence) solutions have been proposed in recent years. Recently, thanks to new XAI evaluation metrics, it has become possible to compare these XAI solutions. However, selecting the most relevant XAI solution among all this diversity is still a tedious task, especially if a user has specific needs and constraints. In this paper, we propose AutoXAI, a framework that recommends the best XAI solution and its hyperparameters according to specified XAI evaluation metrics while considering the user's context (dataset, machine learning model, XAI needs and constraints). It adapts approaches from context-aware recommender systems on one side and strategies of optimization and evaluation from AutoML (Automated Machine Learning) on the other. Through two use cases, we show that AutoXAI recommends XAI solutions adapted to the user's needs with the best hyperparameters matching the user's constraints. CCS CONCEPTS• Computing methodologies → Machine learning.

show abstract

“…Eventually, Vermeire et al [2021] highlights that users should be guided in choosing XAI solutions and proposes a methodology for this issue, while Palacio et al [2021] proposes a theoretical framework to facilitate the comparison between XAI solutions.…”

Section: Approaches For Choosing An Xai Solutionmentioning

confidence: 99%

“…These are tedious and time-consuming tasks. Theoretical guides have been proposed by Vermeire et al [2021], Palacio et al [2021] but, to the best of our knowledge, automating the complete XAI recommendation approach has never been formalized and implemented before.…”

Section: Introductionmentioning

confidence: 99%

Why Should I Choose You? AutoXAI: A Framework for Selecting and Tuning eXplainable AI Solutions

Cugny,

Aligon,

Chevalier

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, a large number of XAI (eXplainable Artificial Intelligence) solutions have been proposed to explain existing ML (Machine Learning) models or to create interpretable ML models. Evaluation measures have recently been proposed and it is now possible to compare these XAI solutions. However, selecting the most relevant XAI solution among all this diversity is still a tedious task, especially when meeting specific needs and constraints. In this paper, we propose AutoXAI, a framework that recommends the best XAI solution and its hyperparameters according to specific XAI evaluation metrics while considering the user's context (dataset, ML model, XAI needs and constraints). It adapts approaches from context-aware recommender systems and strategies of optimization and evaluation from AutoML (Automated Machine Learning). We apply AutoXAI to two use cases, and show that it recommends XAI solutions adapted to the user's needs with the best hyperparameters matching the user's constraints.

show abstract

How to Choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice

Cited by 7 publications

References 13 publications

Explainable AI: roles and stakeholders, desirements and challenges

Explainable AI: roles and stakeholders, desirements and challenges

AutoXAI

Why Should I Choose You? AutoXAI: A Framework for Selecting and Tuning eXplainable AI Solutions

Contact Info

Product

Resources

About