Pluralistic Alignment over Time

Abstract

If an AI system makes decisions over time, how should we evaluate how aligned it is with a group of stakeholders (who may have conflicting values and preferences)? In this position paper, we advocate for consideration of temporal aspects including stakeholders' changing levels of satisfaction and their possibly temporally extended preferences. We suggest how a recent approach to evaluating fairness over time could be applied to a new form of pluralistic alignment: temporal pluralism, where the AI system reflects different stakeholders' values at different times.

Cite

Text

Klassen et al. "Pluralistic Alignment over Time." NeurIPS 2024 Workshops: Pluralistic-Alignment, 2024.

Markdown

[Klassen et al. "Pluralistic Alignment over Time." NeurIPS 2024 Workshops: Pluralistic-Alignment, 2024.](https://mlanthology.org/neuripsw/2024/klassen2024neuripsw-pluralistic/)

BibTeX

@inproceedings{klassen2024neuripsw-pluralistic,
  title     = {{Pluralistic Alignment over Time}},
  author    = {Klassen, Toryn Q. and Alamdari, Parand A. and McIlraith, Sheila A.},
  booktitle = {NeurIPS 2024 Workshops: Pluralistic-Alignment},
  year      = {2024},
  url       = {https://mlanthology.org/neuripsw/2024/klassen2024neuripsw-pluralistic/}
}