OmouAI：基于模拟人格的论证式人机政策审议

中文摘要 AI 辅助

由大型语言模型（LLMs）驱动的智能体之间的辩论已在各种应用中展现出巨大潜力，但当这些互动包含人类参与者并发生在高风险环境中（例如公共政策审议）时，便会受到诸如谄媚行为和缺乏忠实解释等问题困扰。为解决这些问题，我们提出了OmouAI，一个交互式且包容的审议系统，它将LLMs与计算论证相结合——计算论证这一领域擅长在辩论中进行表示与推理。OmouAI允许人类用户与模拟人格（例如代表利益相关者、领域专家或魔鬼代言人）就现实世界挑战进行政策主张的审议，以减少谄媚行为。每个人格生成其自身的论证，所有各方的论证共同构成一个共享的论证框架。用户随后可以对论证提出质疑、添加和修订，从而提供关键的人类监督。然后，论证使用确定性的论证语义针对外部目标（如联合国可持续发展目标）进行评估，从而保证忠实的解释。这些目标的改善或恶化因此作为政策建议的指标。

英文摘要

Debates amongst agents driven by large language models (LLMs) have demonstrated vast potential in various applications, but when these interactions include humans and take place in high-stakes environments, e.g., in public policy deliberations, they are beset with issues such as sycophancy and a lack of faithful explanations. To tackle these issues, we present OmouAI, an interactive and inclusive deliberation system that uses LLMs in combination with computational argumentation, a field which excels in representing and reasoning within debates. OmouAI allows a human user to deliberate policy claims for real-world challenges with simulated personas, e.g., representing stakeholders, domain experts or devil's advocates, towards reducing sycophancy. Each persona generates its own arguments, and the arguments of all parties form a shared argumentation framework. Users can then contest, add and revise arguments, providing crucial human oversight. Then, arguments are evaluated using deterministic argumentative semantics against external goals, such as the UN Sustainable Development Goals, guaranteeing faithful explanations. The advancement or worsening of the goals thus serve as indicators for the policy recommendations.

发表机构

• New Mexico State University（新墨西哥州立大学）
• Washington University in St. Louis（圣路易斯华盛顿大学）
• United Nations University（联合国大学）

机构由 AI 辅助整理，请以论文原文为准。