Beyond Static Snapshots: Dynamic Modeling and Forecasting of Group-Level Value Evolution with Large Language Models
- URL: http://arxiv.org/abs/2602.14043v1
- Date: Sun, 15 Feb 2026 08:14:55 GMT
- Title: Beyond Static Snapshots: Dynamic Modeling and Forecasting of Group-Level Value Evolution with Large Language Models
- Authors: Qiankun Pi, Guixin Su, Jinliang Li, Mayi Xu, Xin Miao, Jiawei Jiang, Ming Zhong, Tieyun Qian,
- Abstract summary: Social simulation is critical for mining complex social dynamics and supporting data-driven decision making.<n>Existing LLM-based approaches predominantly focus on group-level values at discrete time points.<n>We propose a novel framework for group-level dynamic social simulation by integrating historical value trajectories into LLM-based human response modeling.
- Score: 24.234813956858577
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Social simulation is critical for mining complex social dynamics and supporting data-driven decision making. LLM-based methods have emerged as powerful tools for this task by leveraging human-like social questionnaire responses to model group behaviors. Existing LLM-based approaches predominantly focus on group-level values at discrete time points, treating them as static snapshots rather than dynamic processes. However, group-level values are not fixed but shaped by long-term social changes. Modeling their dynamics is thus crucial for accurate social evolution prediction--a key challenge in both data mining and social science. This problem remains underexplored due to limited longitudinal data, group heterogeneity, and intricate historical event impacts. To bridge this gap, we propose a novel framework for group-level dynamic social simulation by integrating historical value trajectories into LLM-based human response modeling. We select China and the U.S. as representative contexts, conducting stratified simulations across four core sociodemographic dimensions (gender, age, education, income). Using the World Values Survey, we construct a multi-wave, group-level longitudinal dataset to capture historical value evolution, and then propose the first event-based prediction method for this task, unifying social events, current value states, and group attributes into a single framework. Evaluations across five LLM families show substantial gains: a maximum 30.88\% improvement on seen questions and 33.97\% on unseen questions over the Vanilla baseline. We further find notable cross-group heterogeneity: U.S. groups are more volatile than Chinese groups, and younger groups in both countries are more sensitive to external changes. These findings advance LLM-based social simulation and provide new insights for social scientists to understand and predict social value changes.
Related papers
- LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations [63.478832978278014]
Large language models (LLMs) are increasingly deployed as autonomous agents, yet evaluations focus primarily on task success rather than cultural appropriateness or evaluator reliability.<n>We introduce LiveCultureBench, a multi-cultural, dynamic benchmark that embeds LLMs as agents in a simulated town and evaluates them on both task completion and adherence to socio-cultural norms.
arXiv Detail & Related papers (2026-03-02T15:04:16Z) - MASim: Multilingual Agent-Based Simulation for Social Science [68.04129327237963]
Multi-agent role-playing has recently shown promise for studying social behavior with language agents.<n>Existing simulations are mostly monolingual and fail to model cross-lingual interaction.<n>We introduce MASim, the first multilingual agent-based simulation framework.
arXiv Detail & Related papers (2025-12-08T06:12:48Z) - Simulating and Experimenting with Social Media Mobilization Using LLM Agents [7.262048441360133]
Building on the landmark 61-million-person Facebook experiment citepbond201261, we develop an agent-based simulation framework.<n>We integrate real U.S. Census demographic distributions, authentic Twitter network topology, and heterogeneous large language model (LLM) agents to examine the effect of mobilization messages on voter turnout.
arXiv Detail & Related papers (2025-10-30T13:43:28Z) - SocioBench: Modeling Human Behavior in Sociological Surveys with Large Language Models [32.66051406264919]
Large language models (LLMs) show strong potential for simulating human social behaviors and interactions, yet lack large-scale, systematically constructed benchmarks for evaluating their alignment with real-world social attitudes.<n>We introduce SocioBench-a comprehensive benchmark derived from the annually collected, standardized survey data of the International Social Survey Programme (ISSP)<n>The benchmark aggregates over 480,000 real respondent records from more than 30 countries, spanning 10 sociological domains and over 40 demographic attributes.
arXiv Detail & Related papers (2025-10-13T08:22:20Z) - Population-Aligned Persona Generation for LLM-based Social Simulation [58.84363795421489]
We propose a systematic framework for synthesizing high-quality, population-aligned persona sets for social simulation.<n>Our approach begins by leveraging large language models to generate narrative personas from long-term social media data.<n>To address the needs of specific simulation contexts, we introduce a task-specific module that adapts the globally aligned persona set to targeted subpopulations.
arXiv Detail & Related papers (2025-09-12T10:43:47Z) - MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework [53.82097200295448]
Mean-Field LLM (MF-LLM) is first to incorporate mean field theory into social simulation.<n>MF-LLM models bidirectional interactions between individuals and the population through an iterative process.<n> IB-Tune is a novel fine-tuning method inspired by the Information Bottleneck principle.
arXiv Detail & Related papers (2025-04-30T12:41:51Z) - SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users [70.02370111025617]
We introduce SocioVerse, an agent-driven world model for social simulation.<n>Our framework features four powerful alignment components and a user pool of 10 million real individuals.<n>Results demonstrate that SocioVerse can reflect large-scale population dynamics while ensuring diversity, credibility, and representativeness.
arXiv Detail & Related papers (2025-04-14T12:12:52Z) - How Social is It? A Benchmark for LLMs' Capabilities in Multi-user Multi-turn Social Agent Tasks [6.487500253901779]
Large language models (LLMs) play roles in multi-user, multi-turn social agent tasks.<n>We propose a novel benchmark, How Social Is It (we call it HSII below), designed to assess LLM's social capabilities.<n>HSII comprises four stages: format parsing, target selection, target switching conversation, and stable conversation, which collectively evaluate the communication and task completion capabilities of LLMs.
arXiv Detail & Related papers (2025-04-04T08:59:01Z) - Social Debiasing for Fair Multi-modal LLMs [59.61512883471714]
Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities.<n>These models often inherit deep-rooted social biases from their training data, leading to uncomfortable responses with respect to attributes such as race and gender.<n>This paper addresses the issue of social biases in MLLMs by introducing a comprehensive counterfactual dataset with multiple social concepts.
arXiv Detail & Related papers (2024-08-13T02:08:32Z) - Training Socially Aligned Language Models on Simulated Social
Interactions [99.39979111807388]
Social alignment in AI systems aims to ensure that these models behave according to established societal values.
Current language models (LMs) are trained to rigidly replicate their training corpus in isolation.
This work presents a novel training paradigm that permits LMs to learn from simulated social interactions.
arXiv Detail & Related papers (2023-05-26T14:17:36Z)
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.