Plurals: A System for Guiding LLMs via Simulated Social Ensembles

• DOI: 10.1145/3706598.3713675
• Publication Date: 2025-04-24T03:17:03Z
• Authors: Joshua Ashkinaze; Emily Fry; Narendra Edara; Eric Gilbert; Ceren Budak
• Keywords: FOS: Computer and information sciences; Computer Science - Computers and Society; Computer Science - Computation and Language; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computers and Society (cs.CY); Computer Science - Human-Computer Interaction; Computer Science - Multiagent Systems; Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)

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. The Plurals library is available at https://github.com/josh-ashkinaze/plurals and will be continually updated.<br/>CHI 2025<br/>