Alignment
Readings on the moral alignment between human values and current data science practices.
Interactions with World
Producing Objects
Processing Objects as Data
Ordering Data as Models to Represent the World
Interpreting Models as Knowledge
| Title | Citation |
|---|---|
| Coded Bias (Documentary) | Kantayya (2020) |
| The Alignment Problem: Machine Learning and Human Values | Christian (2021) |
| Artificial Intelligence, Values, and Alignment | Gabriel (2020) |
| Living Well Together Online: Digital Well-Being from a Confucian Perspective | Dennis & Ziliotti (2023) |
| Envisioning Communities: A Participatory Approach Towards AI for Social Good | Bondi, Xu, Acosta-Navas, & Killian (2021) |
| Aligning Artificial Intelligence with Human Values: Reflections from a Phenomenological Perspective | Han, Kelly, Nikou, & Svee (2021) |
| Challenges of Aligning Artificial Intelligence with Human Values | Sutrop (2020) |
| The Role and Limits of Principles in AI Ethics: Towards a Focus on Tensions | Whittlestone, Nyrup, Alexandrova, & Cave (2019) |
| Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function) | Eckersley (2019) |
| Risk Imposition by Artificial Agents: The Moral Proxy Problem | Thoma (2022) |
References
Bondi, E., Xu, L., Acosta-Navas, D., & Killian, J. (2021, July). Envisioning communities: A participatory approach towards AI for social good. 425–436. https://doi.org/10.1145/3461702.3462612
Christian, B. (2021). The alignment problem. New York, NY: WW Norton.
Dennis, M., & Ziliotti, E. (2023). Living well together online: Digital wellbeing from a confucian perspective. Journal of Applied Philosophy, 40(2), 263–279. https://doi.org/10.1111/japp.12627
Eckersley, P. (2019). Impossibility and uncertainty theorems in AI value alignment (or why your AGI should not have a utility function). arXiv. https://doi.org/10.48550/ARXIV.1901.00064
Gabriel, I. (2020). Artificial intelligence, values, and alignment. Minds and Machines, 30(3), 411–437. https://doi.org/10.1007/s11023-020-09539-2
Han, S., Kelly, E., Nikou, S., & Svee, E.-O. (2021). Aligning artificial intelligence with human values: Reflections from a phenomenological perspective. AI & Society, 37, 1–13. https://doi.org/10.1007/s00146-021-01247-4
Kantayya, S. (Director). (2020). Coded bias. 7th Empire Media.
Sutrop, M. (2020). Challenges of aligning artificial intelligence with human values. Acta Baltica Historiae Et Philosophiae Scientiarum, 8(2), 54–72. https://doi.org/10.11590/abhps.2020.2.04
Thoma, J. (2022). Risk imposition by artificial agents: The moral proxy problem. In S. Voeneky, P. Kellmeyer, O. Mueller, & W. Burgard (Eds.), The cambridge handbook of responsible artificial intelligence: Interdisciplinary perspectives. Cambridge University Press.
Whittlestone, J., Nyrup, R., Alexandrova, A., & Cave, S. (2019, January). The role and limits of principles in AI ethics: Towards a focus on tensions. 195–200. https://doi.org/10.1145/3306618.3314289