# Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks

arXiv: https://arxiv.org/abs/2406.17232 · HTML: https://mlsanity.com/paper/2406.17232/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 11 of 11)

- [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)
- [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)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Systematic Biases in LLM Simulations of Debates](https://mlsanity.com/paper/2402.04049/) (2024)
- [Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information](https://mlsanity.com/paper/2402.18144/) (2024)
- [The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents](https://mlsanity.com/paper/2311.09665/) (2023)

## Built on by (most cited first, 30 of 39)

- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [Benchmarking Distributional Alignment of Large Language Models](https://mlsanity.com/paper/2411.05403/) (2024)
- [Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles](https://mlsanity.com/paper/2502.18968/) (2025)
- [OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation](https://mlsanity.com/paper/2506.05606/) (2025)
- [No Preference Left Behind: Group Distributional Preference Optimization](https://mlsanity.com/paper/2412.20299/) (2024)
- [Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework](https://mlsanity.com/paper/2412.06681/) (2024)
- [Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics](https://mlsanity.com/paper/2506.12657/) (2025)
- [LLM-Based Social Simulations Require a Boundary](https://mlsanity.com/paper/2506.19806/) (2025)
- [Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications](https://mlsanity.com/paper/2505.00049/) (2025)
- [United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory](https://mlsanity.com/paper/2506.06843/) (2025)
- [Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders](https://mlsanity.com/paper/2505.14536/) (2025)
- [Aligning LLM with human travel choices: a persona-based embedding learning approach](https://mlsanity.com/paper/2505.19003/) (2025)
- [PersLLM: A Personified Training Approach for Large Language Models](https://mlsanity.com/paper/2407.12393/) (2024)
- [Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models](https://mlsanity.com/paper/2412.07144/) (2024)
- [HARBOR: Exploring Persona Dynamics in Multi-Agent Competition](https://mlsanity.com/paper/2502.12149/) (2025)
- [Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints](https://mlsanity.com/paper/2506.12421/) (2025)
- [Large Language Models as Psychological Simulators: A Methodological Guide](https://mlsanity.com/paper/2506.16702/) (2025)
- [DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents](https://mlsanity.com/paper/2510.25110/) (2025)
- [PersonaTwin: A Multi-Tier Prompt Conditioning Framework for Generating and Evaluating Personalized Digital Twins](https://mlsanity.com/paper/2508.10906/) (2025)
- [Is artificial intelligence still intelligence? LLMs generalize to novel adjective-noun pairs, but don't mimic the full human distribution](https://mlsanity.com/paper/2410.17482/) (2024)
- [Bridging Language Models and Financial Analysis](https://mlsanity.com/paper/2503.22693/) (2025)
- [Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach](https://mlsanity.com/paper/2601.03534/) (2026)
- [Social Simulacra in the Wild: AI Agent Communities on Moltbook](https://mlsanity.com/paper/2603.16128/) (2026)
- [ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities](https://mlsanity.com/paper/2506.02480/) (2025)
- [Evaluating Steering Techniques using Human Similarity Judgments](https://mlsanity.com/paper/2505.19333/) (2025)
- [Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics](https://mlsanity.com/paper/2508.18600/) (2025)
- [Can Lessons From Human Teams Be Applied to Multi-Agent Systems? The Role of Structure, Diversity, and Interaction Dynamics](https://mlsanity.com/paper/2510.07488/) (2025)
- [PrivacyReasoner: Can LLM Emulate a Human-like Privacy Mind?](https://mlsanity.com/paper/2601.09152/) (2026)
- [From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communities](https://mlsanity.com/paper/2604.03920/) (2026)
- [IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization](https://mlsanity.com/paper/2508.08719/) (2025)

## Abstract (arXiv)

Creating human-like large language model (LLM) agents is crucial for faithful social simulation. Having LLMs role-play based on demographic information sometimes improves human likeness but often does not. This study assessed whether LLM alignment with human behavior can be improved by integrating information from empirically-derived human belief networks. Using data from a human survey, we estimated a belief network encompassing 64 topics loading on nine non-overlapping latent factors. We then seeded LLM-based agents with an opinion on one topic, and assessed the alignment of its expressed opinions on remaining test topics with corresponding human data. Role-playing based on demographic information alone did not align LLM and human opinions, but seeding the agent with a single belief greatly improved alignment for topics related in the belief network, and not for topics outside the network. These results suggest a novel path for human-LLM belief alignment in work seeking to simulate and understand patterns of belief distributions in society.