-------- Forwarded Message --------
Workshop on Transparency and Explanations in Smart Systems (TExSS)
Responsible, Explainable AI for Inclusivity and Trust
Held in conjunction with ACM Intelligent User Interfaces (IUI)
2022, March
20 - 22, University of Helsinki, Finland.
Smart systems that apply complex reasoning to make decisions and
plan
behavior, such as decision support systems and personalized
recommendations,
are difficult for users to understand. A large variety of
algorithms allow
the exploitation of rich and varied data sources, in order to
support human
decision-making and/or taking direct actions. However, there are
increasing
concerns surrounding their transparency and accountability, as
these
processes are typically opaque to the user - e.g., because they
are too
technically complex to be explained or are protected trade
secrets. The
topics of transparency and accountability have attracted
increasing interest
in recent years, aiming at more effective system training, better
reliability and improved usability. This workshop will provide a
venue for
exploring issues that arise in designing, developing and
evaluating
intelligent user interfaces that provide responsible, explainable
AI taking
into account the diversity of the stakeholders involved, and
ensuring trust
through system transparency. Furthermore, understanding users'
fairness
perceptions especially when interacting with such systems (e.g. on
how to
explain systems and models towards ensuring social justice and
trust), will
lead into more effective system interactions, better reliability,
improved
usability and user experience.
Suggested themes include, but are not limited to:
* How can we build inclusive transparency and explanations of
algorithmic systems, particularly those that demonstrate that they
are fair,
accountable, and not biased?
* How different stakeholders perceive algorithmic fairness,
especially
when interacting with AI enabled systems?
* Through explanations, transparency, or other means, how can we
raise
stakeholders' awareness of the potential risk for biases and
social harms
that could result from developing and using intelligent
interactive systems?
* How do different groups of users (e.g. experts, developers,
end-users) perceive the explanations provided by those systems?
* How can we build (good) algorithmic systems, particularly those
that
demonstrate that they are fair and accountable?
* When are the optimal points at which explanations are needed for
transparency?
* What is important in user modeling for system transparency and
explanations?
* What are possible metrics that can be used when evaluating
transparent systems and explanations?
* How can we evaluate explanations and their ability to accurately
explain underlying algorithms and overall systems' behavior,
especially for
the goals of fairness and accountability?
* What techniques can we apply for testing models and assumptions
of
transparent and explainable intelligent interactive systems, being
mindful
of the potential for social and discriminatory harm?
* How can explanations allow human evaluators to select model(s)
that
are unbiased, such as by revealing traits or outcomes of the
underlying
learned system?
* What are important social aspects in interaction design for
system
transparency and explanations?
* How to account for stakeholders' diversity when designing and
evaluating transparency and explanations?
Researchers and practitioners in academia or industry who have an
interest
in these areas are invited to submit papers up to 8 pages (not
including
references) in ACM SIGCHI Paper Format (see
https://iui.acm.org/2022/call_for_papers.html). These submissions
must be
original and relevant contributions. Examples include, but not
limited to,
position papers summarizing authors' existing research in this
area and how
it relates to the workshop theme, papers offering an industrial
perspective
on the workshop theme or a real-world approach to the workshop
theme, papers
that review the related literature and offer a new perspective,
and papers
that describe work-in-progress research projects.
Papers should be submitted via Easychair
(
https://easychair.org/conferences/?conf=texss2022) by the end of
January
3rd 2022, and will be reviewed by committee members. Position
papers do not
need to be anonymized. At least one author of each accepted
position paper
must register for and attend the workshop. It is anticipated that
accepted
contributions will be published in dedicated workshop proceedings.
For
further questions please contact the workshop organizers at
<
texss2022@easychair.org <mailto:texss2022@easychair.org>
>.
Paper authors will present their work as part of thematic panels
followed by
smaller group activities related to the workshop theme. For more
information
visit our website at
<https://explainablesystems.comp.nus.edu.sg/2022/>
https://explainablesystems.comp.nus.edu.sg/2022/
Important Dates
Submission date Jan 3, 2022
Notifications send Jan 28, 2022
Camera-ready Feb 9, 2022
Workshop Date March 22, 2022
Organizing Committee
Tsvi Kuflik Information Systems, The University of Haifa, Haifa,
Israel
Alison Smith-Renner Dataminr, United States
Styliani Kleanthous Loizou Cyprus Centre for Algorithmic
Transparency, Open
University of Cyprus, Nicosia, Cyprus
Jonathan Dodge Oregon State University, Corvallis, Oregon, United
States
Simone Stumpf University of Glasgow, Glasgow, United Kingdom
Min Kyung Lee University of Texas at Austin, Austin, Texas, United
States
Brian Y Lim Department of Computer Science, National University of
Singapore, Singapore
Advait Sarkar Microsoft Research, Cambridge, United Kingdom
Avital Shulner-Tal Information Systems, The University of Haifa,
Haifa,
Israel
Carina Negreanu Microsoft Research, United Kingdom
Tsvika
Tsvi Kuflik, PhD.
Professor of Information Systems
Co-chair of the Digital Humanities BSc program,
Information Systems department,
The University of Haifa
Email:
<mailto:tsvikak@is.haifa.ac.il>
tsvikak@is.haifa.ac.il
Home page:
<https://tsvikak.hevra.haifa.ac.il>
https://tsvikak.hevra.haifa.ac.il
Tel: +972 4 8288511
Fax: +972 4 8288283