Plurals: A System for Guiding LLMs Via Simulated Social Ensembles

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ashkinaze, Joshua, Fry, Emily, Edara, Narendra, Gilbert, Eric, Budak, Ceren
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913752758091776
author Ashkinaze, Joshua
Fry, Emily
Edara, Narendra
Gilbert, Eric
Budak, Ceren
author_facet Ashkinaze, Joshua
Fry, Emily
Edara, Narendra
Gilbert, Eric
Budak, Ceren
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17213
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Plurals: A System for Guiding LLMs Via Simulated Social Ensembles
Ashkinaze, Joshua
Fry, Emily
Edara, Narendra
Gilbert, Eric
Budak, Ceren
Computation and Language
Artificial Intelligence
Computers and Society
Human-Computer Interaction
Multiagent Systems
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.
title Plurals: A System for Guiding LLMs Via Simulated Social Ensembles
topic Computation and Language
Artificial Intelligence
Computers and Society
Human-Computer Interaction
Multiagent Systems
url https://arxiv.org/abs/2409.17213