Plurals: A System for Guiding LLMs Via Simulated Social Ensembles
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.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An OpenNMT Model to Arabic Broken Plurals
Arabic Broken Plurals show an interesting phenomenon in Arabic morphology as they are formed by shifting the consonants of the syllables into different syllable patterns, and subsequently, the pattern of the word changes…
Language AcquisitionmodelPlurals: individuals and sets in a richly typed semantics
We developed a type-theoretical framework for natural lan- guage semantics that, in addition to the usual Montagovian treatment of compositional semantics, includes a treatment of some phenomena of lex- ical semantic: co…
SIGMORPHON–UniMorph 2022 Shared Task 0: Modeling Inflection in Language Acquisition
This year’s iteration of the SIGMORPHONUniMorph shared task on “human-like” morphological inflection generation focuses on generalization and errors in language acquisition. Systems are trained on data sets extracted fro…
Language AcquisitionMorphological InflectionIdentifying Broken Plurals, Irregular Gender, and Rationality in Arabic Text
Data-driven learning of symbolic constraints for a log-linear model in a phonological setting
We propose a non-parametric Bayesian model for learning and weighting symbolically-defined constraints to populate a log-linear model. The model jointly infers a vector of binary constraint values for each candidate outp…
Machine Translation