CS-E400207 - Special Course in Computer Science D: Designing Trustworthy AI Systems and Practices, Lectures, 30.3.2023-8.6.2023
This course space end date is set to 08.06.2023 Search Courses: CS-E400207
Topic outline
-
Session 1 (March 30): Concepts and Models of Trust
-
An Integrative Model of Organizational Trust - Roger C Mayer, and James H Davis. 1995.
-
Trust in Automation: Designing for Appropriate Reliance - John D Lee and Katrina A See. 2004.
Session 2 (April 13): Measuring Trust
- Can You Trust Your Trust Measure? - Meia Chita-Tegmark, Theresa Law, Nicholas Rabb, and Matthias Scheutz. 2021.
-
What Do Survey Measures of Trust Actually Measure? - John Brehm and Meg Savel. 2019.
Session 3 (April 20): Trust in Human & AI Interactions
-
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI - Alon Jacovi, Ana Marasović, Tim Miller, and Yoav Goldberg. 2021
- The relationship between trust in AI and trustworthy machine learning technologies - Toreini et al. 2020
Session 4 (April 27): Designing for Trustworthy Interactions
- Designing for Responsible Trust in AI Systems: A Communication Perspective - Q. Vera Liao and S. Shyam Sundar. 2022.
- Co-Design of a Trustworthy AI System in Healthcare: Deep Learning Based Skin Lesion Classifier - Zicari et al. 2021.
Session 5 (May 4): How Explainability Contributes to Trust in AI
- How Explainability Contributes to Trust in AI - Andrea Ferrario and Michele Loi. 2022.
- Questioning the AI: Informing Design Practices for Explainable AI User Experiences - Q. Vera Liao, Daniel Gruen, and Sarah Miller. 2021.
Session 6 (May 11): Trust in Human-AI Collaboration
- Trust in Collaborative Automation in High Stakes Software Engineering Work: A Case Study at NASA - Widder et al. 2021.
- Capable but Amoral? Comparing AI and Human Expert Collaboration in Ethical Decision Making - Tolmeijer et al. 2022.
- Optional: Integrating AI in Human-Human Collaborative Ideation - Joongi Shin, Janin Koch, Andrés Lucero, Peter Dalsgaard, Wendy E. Mackay. 2023.
Session 7 (May 25): Trust and Privacy in Speech & Conversational AI
- Privacy in Speech Technology - Tom Bäckström (ELEC, Aalto University), in-press 2023.
- The Trustworthiness of Voice Assistants in the Context of Healthcare Investigating the Effect of Perceived Expertise on the Trustworthiness of Voice Assistants, Providers, Data Receivers, and Automatic Speech Recognition - Carolin Wienrichm, Clemens Reitelbach and Astrid Carolus, 2021.
Session 8 (June 1): Trust in LLMs and Responsible AI- Regulating ChatGPT and other Large Generative AI Models - Philipp Hacker, Andreas Engel and Marco Mauer, 2023.
Session 9 (June 8): Final Presentations and Reflections
- Schedule TBD
-