Back to
Schedule
Reading, Analysis and Writeup
This week, your team is learning about AI and the value alignment problem.
In this reflection activity, select one of the papers below on the topic of "AI and Value Alignment", summarize the paper, and describe how the methodologies and ideas of the paper can be applied to analyze/improve your imaginary technology. In addition, describe insights you have drawn from the Q&A session, and what how they apply to your imaginary technology. Your writeup on Overleaf should be 2 pages in total. Please use this
overleaf template for all writeups.
Reading List
● Rama Adithya Varanasi and Nitesh Goyal. 2023.
"It is currently hodgepodge": Examining AI/ML Practitioners’ Challenges during Co-production of Responsible AI Values. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 251, 1–17.
● Qiaosi Wang, Michael Madaio, Shaun Kane, Shivani Kapania, Michael Terry, and Lauren Wilcox. 2023.
Designing Responsible AI: Adaptations of UX Practice to Meet Responsible AI Challenges. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 249, 1–16.
● Cynthia Rudin and Joanna Radin.
Why Are We Using Black Box Models in AI When We Don’t Need To? A Lesson From An Explainable AI Competition. Harvard Data Science Review, 2019.
● Amanda Coston, Anna Kawakami, Haiyi Zhu, Kenneth Holstein, Hoda Heidari.
A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms. In IEEE Conference on Secure and Trustworthy Machine Learning, IEEE SaTML 2023.
● Jonathan Stray, Ivan Vendrov, Jeremy Nixon, Steven Adler and Dylan Hadfield-Menell.
What are you optimizing for? Aligning Recommender Systems with Human Values. 2021.
● Oloff C. Biermann, Ning F. Ma, and Dongwook Yoon. 2022.
From Tool to Companion: Storywriters Want AI Writers to Respect Their Personal Values and Writing Strategies. In Proceedings of the 2022 ACM Designing Interactive Systems Conference (DIS '22). Association for Computing Machinery, New York, NY, USA, 1209–1227.
● Gabriel, Iason. (2020).
Artificial Intelligence, Values, and Alignment. Minds and Machines. 30. 411-437.
● R. Wong.
Using Design Fiction Memos to Analyze UX Professionals’ Values Work Practices: A Case Study Bridging Ethnographic and Design Futuring Methods. In Chi 2021.
● M. Madaio, L. Stark, J. Wortman Vaughan and H. Wallach.
Co-Designing Checklists to Understand Organizational Challenges and Opportunites around Fairness in AI. In CHI 2020.
Presentation
Next week, your team will prepare a 20 minute presentation and lead a 5 minute discussion. During the presentation, you should summarize the paper (15 minutes) and describe how the methodologies / ideas of the paper and the insights you have drawn from the Q&A session can be applied to analyze / improve your imaginary technology (5 minutes).