From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction

2026-09-07

AI Summary

研究使用基于LLM的韩国虚拟人物模拟公共审议，评估其能否反映人口意见模式和通过互动形成结论，发现存在挑战。

Abstract

Multi-agent LLM deliberation has been explored as a scalable way to simulate public deliberation. For such simulations to be informative, persona agents should reflect population opinion patterns and interaction should shape their conclusions. We evaluate whether LLM-based deliberation can meet these two conditions using census-grounded Korean personas debating real policy questions benchmarked against national surveys. Persona agents do not reliably reproduce population opinion patterns: responses are often far more concentrated and frequently reverse demographic differences in the human data. Deliberations nonetheless produce reasoned, reciprocal, and varied arguments alongside substantial stance movement. Yet much of this movement does not require peer exchange: sealed-monologue agents change position at similar rates and reach nearly the same final balance as full debates, while groups initialized with very different positions often converge to similar endpoints. Anchoring population-informed starting positions, meanwhile, sharply suppresses updating. Thus, population representation, argument generation, and interaction-driven opinion change do not necessarily go together. The simulations readily surface arguments on both sides, though whether they capture the diversity of human perspectives remains untested, leaving open a promising role for argument surfacing even as population simulation requires further validation.

Problem

• multi-agent LLM deliberation
• population opinion patterns
• interaction-driven opinion change

Innovation

• multi-agent LLM deliberation
• population opinion patterns
• interaction-driven opinion change