38 Hits in 11.1 sec

What Do We Want From Explainable Artificial Intelligence (XAI)? – A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research [article]

Markus Langer, Daniel Oster, Timo Speith, Holger Hermanns, Lena Kästner, Eva Schmidt, Andreas Sesing, Kevin Baum
2021 pre-print
This model can serve researchers from the variety of different disciplines involved in XAI as a common ground.  ...  Previous research in Explainable Artificial Intelligence (XAI) suggests that a main aim of explainability approaches is to satisfy specific interests, goals, expectations, needs, and demands regarding  ...  We hope that this model inspires and guides future interdisciplinary evaluation and development of explainability approaches and, thereby, further advances XAI research concerning the satisfaction of stakeholders  ... 
doi:10.1016/j.artint.2021.103473 arXiv:2102.07817v1 fatcat:rim6idjyz5e7rc7r7efaybmsnm

The Pragmatic Turn in Explainable Artificial Intelligence (XAI)

Andrés Páez
2019 Minds and Machines  
Aside from providing a clearer objective for XAI, focusing on understanding also allows us to relax the factivity condition on explanation, which is impossible to fulfill in many machine learning models  ...  , and to focus instead on the pragmatic conditions that determine the best fit between a model and the methods and devices deployed to understand it.  ...  Introduction The main goal of Explainable Artificial Intelligence (XAI) has been variously described as a search for explainability, transparency and interpretability, for ways of validating the decision  ... 
doi:10.1007/s11023-019-09502-w fatcat:4h4pyhwocbdvfcm6cnk5pn7aaa

Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review

Anna Markella Antoniadi, Yuhan Du, Yasmine Guendouz, Lan Wei, Claudia Mazo, Brett A. Becker, Catherine Mooney
2021 Applied Sciences  
We propose some guidelines for the implementation of XAI in CDSS and explore some opportunities, challenges, and future research needs.  ...  Machine Learning and Artificial Intelligence (AI) more broadly have great immediate and future potential for transforming almost all aspects of medicine.  ...  Similarly, there is little discussion on the impact of XAI on patients from the patients perspective. These are areas that will benefit from future research.  ... 
doi:10.3390/app11115088 fatcat:rtawp4nsunh7zjr66atz7x63r4

A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts [article]

Gesina Schwalbe, Bettina Finzel
2022 arXiv   pre-print
In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation criteria have been developed within the research field of explainable artificial intelligence (XAI).  ...  In a structured literature analysis and meta-study, we identified and reviewed more than 50 of the most cited and current surveys on XAI methods, metrics, and method traits.  ...  We would like to thank Christian Hellert as well as the anonymous reviewers for their detailed and valuable feedback.  ... 
arXiv:2105.07190v3 fatcat:zy7vl6o4gzcbrpqkrxeyazyeuq

Questioning the AI: Informing Design Practices for Explainable AI User Experiences [article]

Q. Vera Liao, Daniel Gruen, Sarah Miller
2020 arXiv   pre-print
A surge of interest in explainable AI (XAI) has led to a vast collection of algorithmic work on the topic.  ...  To do so, we develop an algorithm-informed XAI question bank in which user needs for explainability are represented as prototypical questions users might ask about the AI, and use it as a study probe.  ...  Zhang, and anonymous CHI 2020 reviewers for their helpful feedback.  ... 
arXiv:2001.02478v1 fatcat:3cm2yzgjrfgxtdcuwx2qfgbkua

Explanation as a social practice: Toward a conceptual framework for the social design of AI systems

Katharina J. Rohlfing, Philipp Cimiano, Ingrid Scharlau, Tobias Matzner, Heike M. Buhl, Hendrik Buschmeier, Elena Esposito, Angela Grimminger, Barbara Hammer, Reinhold Hab-Umbach, Ilona Horwath, Eyke Hullermeier (+8 others)
2020 IEEE Transactions on Cognitive and Developmental Systems  
Building on explanations being a social practice, we present a conceptual framework that aims to guide future research in XAI.  ...  We relate our conceptual framework and our new perspective on explaining to transparency and autonomy as objectives considered for XAI.  ...  We further assume that ER has a model of what she or he intends to explain to EE-that is, a model of what EE needs to understand.  ... 
doi:10.1109/tcds.2020.3044366 fatcat:khrpo6jwljennjj6ucyefqbpwy

Human-Centred Artificial Intelligence for Designing Accessible Cultural Heritage

Galena Pisoni, Natalia Díaz-Rodríguez, Hannie Gijlers, Linda Tonolli
2021 Applied Sciences  
From the literature review analysis, we articulate a conceptual framework that incorporates key elements that constitute museum and cultural heritage online experiences and how these elements are related  ...  artificial intelligence (AI) developments can be used for this aim, i.e.  ...  Acknowledgments: We thank Juan Jesús Pleguezuelos for the motivating testimonies, and Pranav Agarwal, Siham Tabik, Francisco Herrera, Alberto Castillo Lamas, Mario Romero, Serena Ivaldi and Paris Cité  ... 
doi:10.3390/app11020870 fatcat:ny5szod52bd4vkcv74pwbfsv54

One Explanation Does Not Fit All

Kacper Sokol, Peter Flach
2020 Künstliche Intelligenz  
While a variety of interpretability and explainability methods is available, none of them is a panacea that can satisfy all diverse expectations and competing objectives that might be required by the parties  ...  Whenever black-box algorithmic predictions influence human affairs, the inner workings of these algorithms should be scrutinised and their decisions explained to the relevant stakeholders, including the  ...  consisting of both domain experts, approached during the 27 th International Joint Conference on Artificial Intelligence (IJCAI 2018), and a lay audience, approached during a local "Research without Borders  ... 
doi:10.1007/s13218-020-00637-y fatcat:2ix5nv5x75f5ji7xwfyan6maf4

Reporting on Decision-Making Algorithms and some Related Ethical Questions [article]

Benoît Otjacques
2019 arXiv   pre-print
In this paper, we focus on how companies report on risks and ethical issues related to the increasing use of Artificial Intelligence (AI). We explain some of these risks and potential issues.  ...  Next, we identify some recent initiatives by various stakeholders to define a global ethical framework for AI.  ...  The DARPA XAI Programme In 2016, the US Defense Advanced Research Projects Agency (DARPA) has launched a new programme called Explainable Artificial Intelligence (XAI) [4] .  ... 
arXiv:1911.05731v1 fatcat:qf5knbnal5ayvl323rfbl2yt4y

Towards Transparency by Design for Artificial Intelligence

Heike Felzmann, Eduard Fosch-Villaronga, Christoph Lutz, Aurelia Tamò-Larrieux
2020 Science and Engineering Ethics  
With the rise of artificial intelligence (AI) and the ability of AI systems to make automated and self-learned decisions, a call for transparency of how such systems reach decisions has echoed within academic  ...  Finally, we propose a set of nine principles to cover relevant contextual, technical, informational, and stakeholder-sensitive considerations.  ...  paper on artificial intelligence (2020).  ... 
doi:10.1007/s11948-020-00276-4 pmid:33196975 fatcat:xl6o3tcxxrd5zhzr37k4oqpicy

Towards Moral Autonomous Systems [article]

Vicky Charisi and Louise Dennis and Michael Fisher and Robert Lieck and Andreas Matthias and Marija Slavkovik and Janina Sombetzki and Alan F. T. Winfield and Roman Yampolskiy
2017 arXiv   pre-print
We them consider different approaches towards the conceptual design of autonomous systems and their implications on the ethics implementation in such systems.  ...  Then we examine problematic areas regarding the specification and verification of ethical behavior in autonomous systems, particularly with a view towards the requirements of future legislation.  ...  What do we want the system to do? A key problem is specifying what our expectations of an AI system are.  ... 
arXiv:1703.04741v3 fatcat:zsen727f3ngspbzzsi62w52ipy

Human-AI Collaboration in Data Science

Dakuo Wang, Justin D. Weisz, Michael Muller, Parikshit Ram, Werner Geyer, Casey Dugan, Yla Tausczik, Horst Samulowitz, Alexander Gray
2019 Proceedings of the ACM on Human-Computer Interaction  
The rapid advancement of artificial intelligence (AI) is changing our lives in many ways. One application domain is data science.  ...  AutoAI systems are capable of autonomously ingesting and pre-processing data, engineering new features, and creating and scoring models based on a target objectives (e.g. accuracy or run-time efficiency  ...  Data scientists often integrate a wide range of skills from domains including mathematics and statistics, machine learning and artificial intelligence, databases and cloud computing, and data visualization  ... 
doi:10.1145/3359313 fatcat:slieqtiphjbxnlrz5h2dq3gcau

Promoting Ethical Awareness in Communication Analysis: Investigating Potentials and Limits of Visual Analytics for Intelligence Applications [article]

Maximilian T. Fischer, Simon David Hirsbrunner, Wolfgang Jentner, Matthias Miller, Daniel A. Keim, Paula Helm
2022 arXiv   pre-print
In this interdisciplinary work, a joint endeavor of computer scientists, ethicists, and scholars in Science & Technology Studies, we investigate and evaluate opportunities and risks involved in using Visual  ...  We show that finding Visual Analytics design solutions for ethical issues is not a mere optimization task, but balancing out and negotiating these trade-offs has, as we argue, to be an integral aspect  ...  ACKNOWLEDGMENTS The authors acknowledge the financial support by the Federal Ministry of Education and Research of Germany (BMBF) in the framework of PEGASUS under the program "Forschung für die zivile  ... 
arXiv:2203.09859v1 fatcat:xvn5zxix25al7i6u23n4d7zvmm

Ensuring patient and public involvement in the transition to AI‐assisted mental health care: A systematic scoping review and agenda for design justice

Teodor Zidaru, Elizabeth M. Morrow, Rich Stockley
2021 Health Expectations  
Machine-learning algorithms and big data analytics, popularly known as 'artificial intelligence' (AI), are being developed and taken up globally.  ...  (reference and citation tracking); (iii) grey literature; and (iv) inductive thematic analysis, tested at a workshop with health researchers.  ...  Artificial intelligence approaches to predicting and detecting cognitive decline in older adults: a conceptual review.  ... 
doi:10.1111/hex.13299 pmid:34118185 fatcat:i64ljjahnrdkrl3d3ynewbezcu

Towards Designing Explainable Constraint-based Expert Systems

Jan Bode, Max Schemmer, Tomas Balyo
2021 Zenodo  
The importance of Explainable Artificial Intelligence (XAI) is well established.  ...  Nevertheless, current XAI approaches lack stakeholder-centricity and do not take into account insights from the social sciences.  ...  A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research by Langer et al. (2021) .  ... 
doi:10.5281/zenodo.5634104 fatcat:4zp5hw3j6ndnxa5szwoz6gdxti
« Previous Showing results 1 — 15 out of 38 results