Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes

arXiv:2610.05828 · cs.AI · Submitted 2026-10-05 · Read on arXiv

cs.AI

Submitted: 2026-10-05

Updated: 2026-10-06

Comments: Work accepted at REALM EMNLP 2026

Code: https://github.com/amazon-science/data-driven-personas

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Access Regimes — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode

Sources

• Data-Driven Persona-Conditioned Agents for A/B Test Simulation
• From Persona to Personalization: A Survey on Role-Playing Language Agents
• Scaling Synthetic Data Creation with 1,000,000,000 Personas
• The Llama 3 Herd of Models
• AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction
• Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas
• RADIUS: Ranking, Distribution, and Significance - A Comprehensive Alignment Suite for Survey Simulation
• LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
• Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information
• Qwen3 Technical Report

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems