mlsanityData to 7 Oct 2026

Mixture-of-Personas Language Models for Population Simulation

arXiv 2504.05019 ↗First posted 7 Apr 2025cs.LG cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Advances in Large Language Models (LLMs) paved the way for their emerging applications in various domains, such as human behavior simulations, where LLMs could augment human-generated data in social science research and machine learning model training. However, pretrained LLMs often fail to capture the behavioral diversity of target populations due to the inherent variability across individuals and groups. To address this, we propose textitMixture of Personas (MoP), a textitprobabilistic prompting method that aligns the LLM responses with the target population. MoP is a contextual mixture model, where each component is an LM agent characterized by a persona and an exemplar representing subpopulation behaviors. The persona and exemplar are randomly chosen according to the learned mixing weights to elicit diverse LLM responses during simulation. MoP is flexible, requires no model finetuning, and is transferable across base models. Experiments for synthetic data generation show that MoP outperforms competing methods in alignment and diversity metrics.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 19 of its 68 references that are in the map. First posted on arXiv 7 Apr 2025.

Builds on

19 of 68 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  3. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 159
  4. 2020Deep Reinforcement Learning for Intelligent Transportation Systems: A Surveycited by 94
  5. 2019Learning Phase Competition for Traffic Signal Controlcited by 84
  6. 2017Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learningcited by 33
  7. 2021Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal controlcited by 28
  8. 2016Using a Deep Reinforcement Learning Agent for Traffic Signal Controlcited by 26
  9. 2023Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learningcited by 18
  10. 2023Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersectionscited by 9
  11. 2023Large-scale Mixed Traffic Control Using Dynamic Vehicle Routing and Privacy-Preserving Crowdsourcingcited by 9
  12. 2023Mixed Traffic Control and Coordination from Pixelscited by 8
7 more
  1. 2023EnduRL: Enhancing Safety, Stability, and Efficiency of Mixed Traffic Under Real-World Perturbations Via Reinforcement Learningcited by 7
  2. 2024CARL: Congestion-Aware Reinforcement Learning for Imitation-based Perturbations in Mixed Traffic Controlcited by 7
  3. 2024Heterogeneous Mixed Traffic Control and Coordinationcited by 7
  4. 2021Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Modelscited by 6
  5. 2022Time-to-Green predictions for fully-actuated signal control systems with supervised learningcited by 3
  6. 2023Deep Reinforcement Learning for Traffic Light Control in Intelligent Transportation Systemscited by 3
  7. 2017A pedestrian hopping model and traffic light scheduling for pedestrian-vehicle mixed-flow networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 10.

20 papers.

Sort:

By area:

  1. 2025SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Predictioncited by 21
  2. 2025Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectificationcited by 17
  3. 2025Persona-Based Synthetic Data Generation Using Multi-Stage Conditioning with Large Language Models for Emotion Recognitioncited by 5
  4. 2025PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactionscited by 5
  5. 2025CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Modelscited by 5
  6. 2025Structured Pruning for Diverse Best-of-N Reasoning Optimizationcited by 4
  7. 2025Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?cited by 3
  8. 2025Reasoning Planning for Language Modelscited by 2
  9. 2026SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulationcited by 2
  10. 2025IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimizationcited by 1
  11. 2026HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulationcited by 1
  12. 2026Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modelingcited by 1
8 more
  1. 2025From Model Training to Model Raisingcited by 0
  2. 2026LLM Active Alignment: A Nash Equilibrium Perspectivecited by 0
  3. 2026RADIUS: Ranking, Distribution, and Significance - A Comprehensive Alignment Suite for Survey Simulationcited by 0
  4. 2026Adaptive Querying with AI Persona Priorscited by 0
  5. 2026KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learningcited by 0
  6. 2026LLM-Powered Virtual Population for Demand Simulation and Pricingcited by 0
  7. 2026AppLooper: An Agentic Application Engineering Loop for Accountable Release with Virtual-User Feedbackcited by 0
  8. 2026Data-Driven Persona-Conditioned Agents for A/B Test Simulationcited by 0