Summary of Plurals: a System For Guiding Llms Via Simulated Social Ensembles, by Joshua Ashkinaze et al.
Plurals: A System for Guiding LLMs Via Simulated Social Ensembles
by Joshua Ashkinaze, Emily Fry, Narendra Edara, Eric Gilbert, Ceren Budak
First submitted to arxiv on: 25 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces Plurals, a system and Python library for pluralistic AI deliberation. The system consists of language models (LLMs) with personas that deliberate within customizable structures, overseen by moderators. Plurals generates simulated social ensembles and integrates with government datasets to create nationally representative personas. The system includes templates inspired by deliberative democracy and allows users to customize information-sharing structures and deliberation behavior. Six case studies demonstrate the system’s fidelity to theoretical constructs and efficacy. Three randomized experiments show that simulated focus groups produced output resonant with an online sample of relevant audiences in 75% of trials, outperforming zero-shot generation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way for computers to have discussions like humans do. The program is called Plurals and it uses special computer models to make sure many different viewpoints are considered. This helps prevent the model from just repeating what one person thinks. Plurals can be used with real-world data and can create groups that mimic how people discuss topics online. |
Keywords
» Artificial intelligence » Zero shot
