用大模型模拟观点极化，发现偏见越强极化越严重
Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation
- 设计非合作博弈框架，让大模型代理竞争影响人群
- 高确认偏误加剧群体内一致但整体极化更严重
- 重资源反击策略短期有效，长期易耗尽且影响力下降
我们提出一种新颖的非合作博弈框架，用于分析意见形成与抵抗机制，融合社会心理学中的确认偏误、资源约束和影响力惩罚等原则。模拟中，大语言模型（LLM）代理在人群中竞争影响力，并对传播或反驳错误信息的消息施加惩罚。该框架将资源优化纳入代理决策过程。研究发现，更高的确认偏误虽增强群体内部意见一致性，却也加剧整体极化；相反，较低的确认偏误导致意见碎片化且个体信念变化有限。投入大量资源采用高成本辟谣策略虽能短期内使群体倾向辟谣代理，但会迅速耗尽资源，降低长期影响力。
原文摘要 · Abstract (English)
We introduce a novel non-cooperative game to analyse opinion formation and resistance, incorporating principles from social psychology such as confirmation bias, resource constraints, and influence penalties. Our simulation features Large Language Model (LLM) agents competing to influence a population, with penalties imposed for generating messages that propagate or counter misinformation. This framework integrates resource optimisation into the agents' decision-making process. Our findings demonstrate that while higher confirmation bias strengthens opinion alignment within groups, it also exacerbates overall polarisation. Conversely, lower confirmation bias leads to fragmented opinions and limited shifts in individual beliefs. Investing heavily in a high-resource debunking strategy can initially align the population with the debunking agent, but risks rapid resource depletion and diminished long-term influence
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。