用平均场理论让大模型模拟群体决策动态，更贴近真实社会行为。
MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework
- 引入平均场理论，让个体与群体双向交互迭代生成行为轨迹。
- 在真实数据上使群体分布差异降低47%，显著提升预测准确性。
- 适用于跨领域社会仿真，适合政策制定与行为干预研究者。
群体决策模拟不仅依赖个体行为聚合，更源于个体间的动态互动。尽管大语言模型（LLMs）在社会模拟中潜力巨大，但与真实数据的定量一致性仍是挑战。为此，我们提出首个将平均场理论融入LLM的社会模拟框架——均值场大语言模型（MF-LLM）。MF-LLM通过迭代过程建模个体与群体之间的双向交互：群体信号指导个体决策，个体行为又反向更新群体信号，从而生成连贯的集体行为轨迹。为增强与真实数据的对齐，我们提出受信息瓶颈原理启发的IB-Tune微调方法，保留对未来行为最具预测力的群体信号，过滤冗余历史。在真实社会数据集上的评估显示，相较于非均值场基线，MF-LLM将群体分布的KL散度降低47%，实现精准趋势预测与有效干预规划。该框架在7个领域和4种LLM骨干网络上均表现稳健，提供可扩展、高保真的社会模拟基础。
原文摘要 · Abstract (English)
Simulating collective decision-making involves more than aggregating individual behaviors; it emerges from dynamic interactions among individuals. While large language models (LLMs) offer strong potential for social simulation, achieving quantitative alignment with real-world data remains a key challenge. To bridge this gap, we propose the Mean-Field LLM (MF-LLM) framework, the first to incorporate mean field theory into LLM-based social simulation. MF-LLM models bidirectional interactions between individuals and the population through an iterative process, generating population signals to guide individual decisions, which in turn update the signals. This interplay produces coherent trajectories of collective behavior. To improve alignment with real-world data, we introduce IB-Tune, a novel fine-tuning method inspired by the Information Bottleneck principle, which retains population signals most predictive of future actions while filtering redundant history. Evaluated on a real-world social dataset, MF-LLM reduces KL divergence to human population distributions by 47\% compared to non-mean-field baselines, enabling accurate trend forecasting and effective intervention planning. Generalizing across 7 domains and 4 LLM backbones, MF-LLM provides a scalable, high-fidelity foundation for social simulation.
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。