paper-with-me

Papers

Pluralistic Alignment Over Time

2024-11-16 · Toryn Q. Klassen, Parand A. Alamdari, Sheila A. McIlraith

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.

📄 PDF Abstract BibTeX arXiv:2411.10654

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessPosition

Similar Papers 제목 키워드 기반

A Roadmap to Pluralistic Alignment

2024-02-07 · Taylor Sorensen, Jared Moore, Jillian Fisher, Mitchell Gordon 외

With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic huma…

Pluralistic Off-policy Evaluation and Alignment

2025-09-15 · Chengkai Huang, Junda Wu, Zhouhang Xie, Yu Xia 외 arxiv

Personalized preference alignment for LLMs with diverse human preferences requires evaluation and alignment methods that capture pluralism. Most existing preference alignment datasets are logged under policies that diffe…

Response Generation

Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI

2024-11-15 · Parand A. Alamdari, Toryn Q. Klassen, Rodrigo Toro Icarte, Sheila A. McIlraith

Pluralistic alignment is concerned with ensuring that an AI system's objectives and behaviors are in harmony with the diversity of human values and perspectives. In this paper we study the notion of pluralistic alignment…

Diversity

Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy

2026-05-02 · Rachel Freedman arxiv

Prevailing alignment methods target a fixed set of preferences and therefore risk forcing value lock-in as societal norms evolve over time. We introduce Adaptive Pluralistic Alignment (APA), a modular pipeline for updati…

VISPA: Pluralistic Alignment via Automatic Value Selection and Activation

2026-01-19 · Shenyan Zheng, Jiayou Zhong, Anudeex Shetty, Heng Ji 외 arxiv

As large language models are increasingly used in high-stakes domains, it is essential that their outputs reflect not average} human preference, rather range of varying perspectives. Achieving such pluralism, however, re…