Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human 
Feedback

Conitzer, Vincent; Freedman, Rachel; Heitzig, Jobst; Holliday, Wesley H.; Jacobs, Bob M.; Lambert, Nathan; Mossé, Milan; Pacuit, Eric; Russell, Stuart; Schoelkopf, Hailey; Tewolde, Emanuel; Zwicker, William S.

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Book Chapter

Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback

Authors

Conitzer, Vincent
External Organizations;

Freedman, Rachel
External Organizations;

/persons/resource/heitzig

Heitzig, Jobst
Potsdam Institute for Climate Impact Research;

Holliday, Wesley H.
External Organizations;

Jacobs, Bob M.
External Organizations;

Lambert, Nathan
External Organizations;

Mossé, Milan
External Organizations;

Pacuit, Eric
External Organizations;

Russell, Stuart
External Organizations;

Schoelkopf, Hailey
External Organizations;

Tewolde, Emanuel
External Organizations;

Zwicker, William S.
External Organizations;

External Ressource

https://proceedings.mlr.press/v235/conitzer24a.html
(Publisher version)

https://doi.org/10.48550/arXiv.2404.10271
(Preprint)

Fulltext (public)

There are no public fulltexts stored in PIKpublic

Supplementary Material (public)

There is no public supplementary material available

Citation

Conitzer, V., Freedman, R., Heitzig, J., Holliday, W. H., Jacobs, B. M., Lambert, N., Mossé, M., Pacuit, E., Russell, S., Schoelkopf, H., Tewolde, E., Zwicker, W. S. (2024): Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback. - In: Salakhutdinov, R., Kolter, Z., Heller, K., Weller, A., Oliver, N., Scarlett, J., Berkenkamp, F. (Eds.), Proceedings of the 41st International Conference on Machine Learning, (Proceedings of Machine Learning Research ; 235), Cambridge, MA : MRL Press, 9346-9360.

Cite as: https://publications.pik-potsdam.de/pubman/item/item_29847

Abstract

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans’ expressed preferences over multiple outputs. Another approach is constitutional AI, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How can we aggregate the input into consistent data about “collective” preferences or otherwise use it to make collective choices about model behavior? In this paper, we argue that the field of social choice is well positioned to address these questions, and we discuss ways forward for this agenda, drawing on discussions in a recent workshop on Social Choice for AI Ethics and Safety held in Berkeley, CA, USA in December 2023.