# LLMs generate structurally realistic social networks but overestimate political homophily

arXiv: https://arxiv.org/abs/2408.16629 · HTML: https://mlsanity.com/paper/2408.16629/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 95 references that are in the map.
- First posted on arXiv 29 Aug 2024.

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders](https://mlsanity.com/paper/1802.03480/) (2018)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs](https://mlsanity.com/paper/2307.03393/) (2023)
- [Can Language Models Solve Graph Problems in Natural Language?](https://mlsanity.com/paper/2305.10037/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Language is All a Graph Needs](https://mlsanity.com/paper/2308.07134/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Cooperative Game Theory Approaches for Network Partitioning](https://mlsanity.com/paper/1707.03587/) (2017)
- [GraphText: Graph Reasoning in Text Space](https://mlsanity.com/paper/2310.01089/) (2023)
- [Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models](https://mlsanity.com/paper/2402.04614/) (2024)
- [CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations](https://mlsanity.com/paper/2310.11501/) (2023)
- [A Systematic Survey on Deep Generative Models for Graph Generation](https://mlsanity.com/paper/2007.06686/) (2020)

## Built on by (most cited first, 30 of 33)

- [LLM Generated Persona is a Promise with a Catch](https://mlsanity.com/paper/2503.16527/) (2025)
- [MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations](https://mlsanity.com/paper/2504.07830/) (2025)
- [Emergence of polarization in networks of large language model agents](https://mlsanity.com/paper/2501.05171/) (2025)
- [Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancy](https://mlsanity.com/paper/2503.09639/) (2025)
- [Social Opinions Prediction Utilizes Fusing Dynamics Equation with LLM-based Agents](https://mlsanity.com/paper/2409.08717/) (2024)
- [LLM-Based Multi-Agent Systems are Scalable Graph Generative Models](https://mlsanity.com/paper/2410.09824/) (2024)
- [A Large-Scale Simulation on Large Language Models for Decision-Making in Political Science](https://mlsanity.com/paper/2412.15291/) (2024)
- [The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models](https://mlsanity.com/paper/2604.24698/) (2026)
- [Are LLM-Powered Social Media Bots Realistic?](https://mlsanity.com/paper/2508.00998/) (2025)
- [Don't Trust Generative Agents to Mimic Communication on Social Networks Unless You Benchmarked their Empirical Realism](https://mlsanity.com/paper/2506.21974/) (2025)
- [Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacy](https://mlsanity.com/paper/2504.00241/) (2025)
- [Learning to Make Friends: Coaching LLM Agents toward Emergent Social Ties](https://mlsanity.com/paper/2510.19299/) (2025)
- [Gender Dynamics and Homophily in a Social Network of LLM Agents](https://mlsanity.com/paper/2602.02606/) (2026)
- [Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility](https://mlsanity.com/paper/2602.04674/) (2026)
- [Simulating and Experimenting with Social Media Mobilization Using LLM Agents](https://mlsanity.com/paper/2510.26494/) (2025)
- [Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines](https://mlsanity.com/paper/2512.11844/) (2025)
- [An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agents](https://mlsanity.com/paper/2602.03775/) (2026)
- [DynaGRAG | Exploring the Topology of Information for Advancing Language Understanding and Generation in Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.18644/) (2024)
- [Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studies](https://mlsanity.com/paper/2505.22981/) (2025)
- [HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulation](https://mlsanity.com/paper/2601.05656/) (2026)
- [When Do LLMs Generate Realistic Social Networks? A Multi-Dimensional Study of Culture, Language, Scale, and Method](https://mlsanity.com/paper/2605.12898/) (2026)
- [Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI-Generated and Human Data](https://mlsanity.com/paper/2505.21997/) (2025)
- [Large language models for spreading dynamics in complex systems](https://mlsanity.com/paper/2602.08085/) (2026)
- [Causal Effects with Unobserved Unit Types in Interacting Human-AI Systems](https://mlsanity.com/paper/2603.01339/) (2026)
- [Collective Opinion Dynamics in Structured LLM Populations](https://mlsanity.com/paper/2604.11312/) (2026)
- [Can LLM Agents Simulate Dynamic Networks? A Case Study on Email Networks with Phishing Synthesis](https://mlsanity.com/paper/2605.12507/) (2026)
- [Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale](https://mlsanity.com/paper/2606.30801/) (2026)
- [Evaluating the Effectiveness of Persona Simulation in Opinion Prediction with GPT-4.1](https://mlsanity.com/paper/2607.20589/) (2026)
- [Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models](https://mlsanity.com/paper/2608.08199/) (2026)
- [LLMs for Social Network Modeling: From Network Generation to Dynamic Processes](https://mlsanity.com/paper/2609.08049/) (2026)

## Abstract (arXiv)

Generating social networks is essential for many applications, such as epidemic modeling and social simulations. The emergence of generative AI, especially large language models (LLMs), offers new possibilities for social network generation: LLMs can generate networks without additional training or need to define network parameters, and users can flexibly define individuals in the network using natural language. However, this potential raises two critical questions: 1) are the social networks generated by LLMs realistic, and 2) what are risks of bias, given the importance of demographics in forming social ties? To answer these questions, we develop three prompting methods for network generation and compare the generated networks to a suite of real social networks. We find that more realistic networks are generated with "local" methods, where the LLM constructs relations for one persona at a time, compared to "global" methods that construct the entire network at once. We also find that the generated networks match real networks on many characteristics, including density, clustering, connectivity, and degree distribution. However, we find that LLMs emphasize political homophily over all other types of homophily and significantly overestimate political homophily compared to real social networks.