Persona Prompting
Overview
Persona prompting studies how descriptions of a model’s role, background, values, or preferences can steer its answers, recommendations, and decisions. Common approaches include expert-role prompts, personas grounded in survey data, and retrieval methods that select relevant roles; evaluations span survey prediction, recommendation, bias audits, and multimodal tasks. Persona prompts can shift outputs, but effects vary by model and task, and gains in one measure may come with costs in clarity, factuality, or diversity. A central open question is whether prompts produce reliable, human-faithful behavior or mainly alter surface wording without changing underlying biases or preferences.
Latest papers
24 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.