Building Social World Models with Large Language Models

• URL: http://arxiv.org/abs/2606.11482v1
• Date: Tue, 09 Jun 2026 22:15:51 GMT
• Title: Building Social World Models with Large Language Models
• Abstract summary: We introduce the concept of the Social World Model (SWM), a general framework designed to capture how social beliefs evolve in response to major events.<n>SWM learns state-transition functions for social beliefs by mining temporal patterns in social data and optimizing the evidence lower bound.<n>Our experimental results show that SWM significantly outperforms time-series foundation models.
• Score: 30.649793661278277
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding and predicting how social beliefs evolve in response to events -- from policy changes to scientific breakthroughs -- remains a fundamental challenge in social science. Given LLMs' commonsense knowledge and social intelligence, we ask: Can LLMs model the dynamics of social beliefs following social events? In this work, we introduce the concept of the Social World Model (SWM), a general framework designed to capture how social beliefs evolve in response to major events. SWM learns state-transition functions for social beliefs by mining temporal patterns in social data and optimizing the evidence lower bound, without the need for explicit human annotations linking events to belief shifts, or for expensive census data. To evaluate SWM, we introduce a benchmark, SWM-bench, derived from real-world prediction markets, specifically Kalshi and Polymarket. SWM-bench includes over 12k data points for social belief prediction tasks spanning diverse domains such as politics, finance, and cryptocurrency. Our experimental results show that SWM significantly outperforms time-series foundation models, achieving state-of-the-art results on Kalshi data and demonstrating competitive performance on Polymarket data, while offering interpretable insights into the underlying mechanisms of social belief dynamics.

Related papers

• Neural Synchrony Between Socially Interacting Language Models [52.74586779814636]
  Large language models (LLMs) are widely accepted as powerful approximations of human behavior.<n>It remains controversial whether they can be meaningfully compared to human social minds.
  arXiv  Detail & Related papers  (2026-02-19T20:33:54Z)
• Beyond Static Snapshots: Dynamic Modeling and Forecasting of Group-Level Value Evolution with Large Language Models [24.234813956858577]
  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.
  arXiv  Detail & Related papers  (2026-02-15T08:14:55Z)
• Social Simulations with Large Language Model Risk Utopian Illusion [61.358959720048354]
  We introduce a systematic framework for analyzing large language models' behavior in social simulation.<n>Our approach simulates multi-agent interactions through chatroom-style conversations and analyzes them across five linguistic dimensions.<n>Our findings reveal that LLMs do not faithfully reproduce genuine human behavior but instead reflect overly idealized versions of it.
  arXiv  Detail & Related papers  (2025-10-24T06:08:41Z)
• SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models [41.68365456601248]
  We introduce SocialMaze, a new benchmark specifically designed to evaluate social reasoning.<n>SocialMaze systematically incorporates three core challenges: deep reasoning, dynamic interaction, and information uncertainty.<n>It provides six diverse tasks across three key settings: social reasoning games, daily-life interactions, and digital community platforms.
  arXiv  Detail & Related papers  (2025-05-29T17:47:36Z)
• SCRAG: Social Computing-Based Retrieval Augmented Generation for Community Response Forecasting in Social Media Environments [8.743208265682014]
  SCRAG is a prediction framework inspired by social computing.<n>It forecast community responses to real or hypothetical social media posts.<n>It can be used by public relations specialists to craft messaging in ways that avoid unintended misinterpretations.
  arXiv  Detail & Related papers  (2025-04-18T15:02:31Z)
• 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)
• Social Genome: Grounded Social Reasoning Abilities of Multimodal Models [61.88413918026431]
  Social reasoning abilities are crucial for AI systems to interpret and respond to multimodal human communication and interaction within social contexts.<n>We introduce SOCIAL GENOME, the first benchmark for fine-grained, grounded social reasoning abilities of multimodal models.
  arXiv  Detail & Related papers  (2025-02-21T00:05:40Z)
• Social Opinions Prediction Utilizes Fusing Dynamics Equation with LLM-based Agents [6.1923703280119105]
  This study proposes the Fusing Dynamics Equation-Large Language Model (FDE-LLM) algorithm.<n>This innovative approach aligns the actions and evolution of opinions in Large Language Models with the real-world data on social networks.<n>Our algorithm accurately simulates the decay and recovery of opinions over time.
  arXiv  Detail & Related papers  (2024-09-13T11:02:28Z)
• 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)
• PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception [50.551003004553806]
  We create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions. Phase is validated with human experiments demonstrating that humans perceive rich interactions in the social events. As a baseline model, we introduce a Bayesian inverse planning approach, SIMPLE, which outperforms state-of-the-art feed-forward neural networks.
  arXiv  Detail & Related papers  (2021-03-02T18:44:57Z)

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.