When Persona Attributes Improve Population Alignment in Large Language Models

arXiv:2609.02526 · cs.CL, cs.CY · Submitted 2026-09-02 · Read on arXiv

cs.CL, cs.CY

Submitted: 2026-09-02

Updated: 2026-09-02

Terminology

• Alignment — 53× in this paper · explained in 1 episode
• Persona Prompting — 53× in this paper · explained in 2 episodes
• Natural Language Processing — 5× in this paper
• Semantic Similarity — 5× in this paper · explained in 2 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Generalizability — 4× in this paper · explained in 6 episodes
• German General Social Survey — 4× in this paper
• Jensen-Shannon Distance — 4× in this paper
• Benchmark — 2× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• World Value Survey — 2× in this paper
• AI Alignment — 1× in this paper · explained in 2 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Digital Twin — 1× in this paper · explained in 5 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Feature Selection — 1× in this paper · explained in 4 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Sycophancy — 1× in this paper · explained in 4 episodes
• US General Social Survey — 1× in this paper

Sources

• Evaluating how LLM annotations represent diverse views on contentious topics
• Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
• Persona-Based Simulation of Human Opinion at Population Scale
• LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering