MF-LLM: Simulating Collective Decision Dynamics via a Mean-Field Large Language Model Framework

• URL: http://arxiv.org/abs/2504.21582v1
• Date: Wed, 30 Apr 2025 12:41:51 GMT
• Title: MF-LLM: Simulating Collective Decision Dynamics via a Mean-Field Large Language Model Framework
• Authors: Qirui Mi, Mengyue Yang, Xiangning Yu, Zhiyu Zhao, Cheng Deng, Bo An, Haifeng Zhang, Xu Chen, Jun Wang,
• Abstract summary: Mean-Field LLM (MF-LLM) framework explicitly models the feedback loop between micro-level decisions and macro-level population.<n>MF-LLM alternates between two models: a policy model that generates individual actions based on personal states and group-level information, and a mean field model that updates the population distribution.<n>We evaluate MF-LLM on a real-world social dataset, where it reduces KL divergence to human population distributions by 47 percent over non-mean-field baselines.
• Score: 53.82097200295448
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Simulating collective decision-making involves more than aggregating individual behaviors; it arises from dynamic interactions among individuals. While large language models (LLMs) show promise for social simulation, existing approaches often exhibit deviations from real-world data. To address this gap, we propose the Mean-Field LLM (MF-LLM) framework, which explicitly models the feedback loop between micro-level decisions and macro-level population. MF-LLM alternates between two models: a policy model that generates individual actions based on personal states and group-level information, and a mean field model that updates the population distribution from the latest individual decisions. Together, they produce rollouts that simulate the evolving trajectories of collective decision-making. To better match real-world data, we introduce IB-Tune, a fine-tuning method for LLMs grounded in the information bottleneck principle, which maximizes the relevance of population distributions to future actions while minimizing redundancy with historical data. We evaluate MF-LLM on a real-world social dataset, where it reduces KL divergence to human population distributions by 47 percent over non-mean-field baselines, and enables accurate trend forecasting and intervention planning. It generalizes across seven domains and four LLM backbones, providing a scalable foundation for high-fidelity social simulation.

Related papers

• Mixture-of-Personas Language Models for Population Simulation [20.644911871150136]
  Large Language Models (LLMs) can augment human-generated data in social science research and machine learning model training.<n>MoP is a contextual mixture model, where each component is an LM agent characterized by a persona and an exemplar representing subpopulation behaviors.<n>MoP is flexible, requires no model finetuning, and is transferable across base models.
  arXiv  Detail & Related papers  (2025-04-07T12:43:05Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Client Contribution Normalization for Enhanced Federated Learning [4.726250115737579]
  Mobile devices, including smartphones and laptops, generate decentralized and heterogeneous data. Federated Learning (FL) offers a promising alternative by enabling collaborative training of a global model across decentralized devices without data sharing. This paper focuses on data-dependent heterogeneity in FL and proposes a novel approach leveraging mean latent representations extracted from locally trained models.
  arXiv  Detail & Related papers  (2024-11-10T04:03:09Z)
• Social Debiasing for Fair Multi-modal LLMs [55.8071045346024]
  Multi-modal Large Language Models (MLLMs) have advanced significantly, offering powerful vision-language understanding capabilities. However, these models often inherit severe social biases from their training datasets, leading to unfair predictions based on attributes like race and gender. This paper addresses the issue of social biases in MLLMs by i) Introducing a comprehensive Counterfactual dataset with Multiple Social Concepts (CMSC) and ii) Proposing an Anti-Stereotype Debiasing strategy (ASD)
  arXiv  Detail & Related papers  (2024-08-13T02:08:32Z)
• Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models [83.02797560769285]
  Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data.<n>Current methods often overlook the heterogeneity among pre-trained models, which leads to performance degradation due to task conflicts.
  arXiv  Detail & Related papers  (2024-05-26T13:11:55Z)
• Improving Group Connectivity for Generalization of Federated Deep Learning [8.594665698279522]
  Federated learning (FL) involves multiple clients collaboratively training a global model via iterative local updates and model fusion. In this paper, we study and improve FL's generalization through a fundamental connectivity'' perspective. We propose FedGuCci and FedGuCci+, improving group connectivity for better generalization.
  arXiv  Detail & Related papers  (2024-02-29T08:27:01Z)
• EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning [15.124439914522693]
  Federated Learning (FL) is a decentralized machine learning paradigm that enables collaborative model training across dispersed nodes. This paper presents EvoFed, a novel approach that integrates Evolutionary Strategies (ES) with FL to address these challenges.
  arXiv  Detail & Related papers  (2023-11-13T17:25:06Z)
• On the steerability of large language models toward data-driven personas [98.9138902560793]
  Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs.
  arXiv  Detail & Related papers  (2023-11-08T19:01:13Z)
• FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation [32.36334319329364]
  Cross-silo federated learning (FL) enables the development of machine learning models on datasets distributed across data centers. Recent research has found that current FL algorithms face a trade-off between local and global performance when confronted with distribution shifts. We propose a novel federated model soup method to optimize the trade-off between local and global performance.
  arXiv  Detail & Related papers  (2023-07-20T00:07:29Z)
• Non-Invasive Fairness in Learning through the Lens of Data Drift [88.37640805363317]
  We show how to improve the fairness of Machine Learning models without altering the data or the learning algorithm. We use a simple but key insight: the divergence of trends between different populations, and, consecutively, between a learned model and minority populations, is analogous to data drift. We explore two strategies (model-splitting and reweighing) to resolve this drift, aiming to improve the overall conformance of models to the underlying data.
  arXiv  Detail & Related papers  (2023-03-30T17:30:42Z)
• Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning [112.69497636932955]
  Federated learning aims to train models across different clients without the sharing of data for privacy considerations. We study how data heterogeneity affects the representations of the globally aggregated models. We propose sc FedDecorr, a novel method that can effectively mitigate dimensional collapse in federated learning.
  arXiv  Detail & Related papers  (2022-10-01T09:04:17Z)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.