让AI模拟多元观点辩论，提升决策代表性。
Plurals: A System for Guiding LLMs Via Simulated Social Ensembles
- 用带身份的LLM组成虚拟讨论组，按民主议事规则协作
- 实验显示其输出与真实人群意见匹配度达75%
- 适合政策制定、社会议题研究等需要多视角的场景
近期争议指出语言模型可能偏向特定立场。但若不追求‘无立场’，而是利用多元观点呢？我们提出Plurals，一个支持多元主义人工智能讨论的系统与Python库。Plurals由带角色设定的代理（LLMs）组成，在可定制的结构中通过主持人监督进行讨论，生成模拟社会群体。系统整合政府数据创建全国代表性身份，采用源自协商民主的讨论模板，并允许用户自定义信息共享结构与行为规则。六个案例研究验证了理论构念的保真度与有效性。三项随机实验表明，模拟焦点小组的输出在75%情况下优于零样本生成，且与目标受众在线样本高度一致。Plurals既是范式也是可运行系统，代码已开源并持续更新。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。