Plurals: A System for Guiding LLMs via Simulated Social Ensembles

要旨

Recent debates raised concerns that language models may favor certain viewpoints. But what if the solution is not to aim for a "view from nowhere'' but rather to leverage different viewpoints? We introduce Plurals, a system and Python library for pluralistic AI deliberation. Plurals consists of Agents (LLMs, optionally with personas) which deliberate within customizable Structures, with Moderators overseeing deliberation. Plurals is a generator of simulated social ensembles. Plurals integrates with government datasets to create nationally representative personas, includes deliberation templates inspired by deliberative democracy, and allows users to customize both information-sharing structures and deliberation behavior within Structures. Six case studies demonstrate fidelity to theoretical constructs and efficacy. Three randomized experiments show simulated focus groups produced output resonant with an online sample of the relevant audiences (chosen over zero-shot generation in 75% of trials). Plurals is both a paradigm and a concrete system for pluralistic AI.

受賞
Honorable Mention
著者
Joshua Ashkinaze
University of Michigan, Ann Arbor, Michigan, United States
Emily Fry
Oakland Community College, Auburn Hills, Michigan, United States
Narendra Edara
University of Michigan, Ann Arbor, Michigan, United States
Eric Gilbert
University of Michigan, Ann Arbor, Michigan, United States
Ceren Budak
University of Michigan, Ann Arbor, Michigan, United States
DOI

10.1145/3706598.3713675

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713675

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: DeIving into LLMs

G303
7 件の発表
2025-04-29 20:10:00
2025-04-29 21:40:00
日本語まとめ
読み込み中…