Year: 2025
Type: preprint
Abstract: AI alignment, the challenge of ensuring AI systems act in accordance with human values, has emerged as a critical problem in the development of systems such as foundation models and recommender systems. Still, the current dominant approach, reinforcement learning with human feedback (RLHF) faces known theoretical limitations in aggregating diverse human preferences. Social choice theory provides a framework to aggregate preferences, but was not developed for the multidimensional applications typical of AI. Leveraging insights from a recently published urn process, this work introduces a preference aggregation strategy that adapts to the user's context and that inherits the good properties of the maximal lottery, a Condorcet-consistent solution concept.
Source: arXiv (Cornell University)
Author: Heymann, Benjamin
Language: English
Subfield: Economics and Econometrics
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W4416038733
Cites:
Cited by:
Related to: