Get Started
Home
Topics
Search
Library
Research questionWhen does persona prompting improve LLM survey-response prediction, and how should attributes be selected?Persona prompting has produced inconsistent gains in survey prediction, and adding more attributes does not reliably improve alignment. It remains unclear whether gains depend on the variation in human responses or on how persona attributes are selected.
AI
Evaluation & Benchmarks
Machine Learning
Natural Language Processing
Latest papersRecent research connected to this question, newest first.When Persona Attributes Improve Population Alignment in Large Language ModelsThe evidence concerns general social-survey prediction across four surveys in two countries, six LLMs, and twenty prediction tasks per survey. It compares different persona-attribute selection methods; the input does not specify the individual models or the full selection procedures.research paper · Sep 2, 2026
Related questions
How can persona-based dialogue systems use persona information only when it is relevant to the conversation?How reliably do human psychometric questionnaires predict LLM behavior in realistic user interactions?How can personalized dialogue agents keep evolving user personas traceable to supporting events during retrieval?How can we assess whether LLM-generated personas reproduce culturally conditioned worldviews and moral values?