Pluralistic Alignment Over Time

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Klassen, Toryn Q., Alamdari, Parand A., McIlraith, Sheila A.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916485371265024
author Klassen, Toryn Q.
Alamdari, Parand A.
McIlraith, Sheila A.
author_facet Klassen, Toryn Q.
Alamdari, Parand A.
McIlraith, Sheila A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10654
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Pluralistic Alignment Over Time
Klassen, Toryn Q.
Alamdari, Parand A.
McIlraith, Sheila A.
Artificial Intelligence
Computers and Society
Machine Learning
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.
title Pluralistic Alignment Over Time
topic Artificial Intelligence
Computers and Society
Machine Learning
url https://arxiv.org/abs/2411.10654