Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

Persona effect

The persona effect refers to the measurable change in an artificial intelligence model's outputs, behaviors, or decision patterns when it is prompted or conditioned to adopt a specific identity defined by demographic, social, or behavioral attributes. In computational linguistics and simulated social research, the persona effect describes how assigning distinct profiles enables large language models to emulate diverse human perspectives, subjective attitudes, and demographic variations. The strength of this effect generally depends on the degree to which the specified identity characteristics correlate with real-world human responses in a given context, allowing models to approximate nuanced differences in human opinions and annotation tasks when background variables play an explanatory role.

1 item

Quantifying the Persona Effect in LLM Simulations

Quantifying the Persona Effect in LLM Simulations

Tiancheng Hu, Nigel Collier

OrganizationsUniversity of Cambridge

Why you should read this

Quantifies the limits and efficacy of persona prompting across subjective NLP tasks, establishing that demographic variables explain under ten percent of annotation variance yet enable large language models to recover most predictable human variation when strong correlations exist.

Large language models (LLMs) have shown remarkable promise in simulating human language and behavior. This study investigates how integrating persona variables—demographic, social, and behavioral factors—impacts LLMs’ ability to simulate diverse perspectives. We find that persona variables account for <10% variance in annotating existing subjective NLP datasets. Nonetheless, incorporating persona variables via prompting in LLMs provides modest but statistically significant improvements. Persona prompting is most effective in samples where many annotators disagree, but their disagreements are relatively minor. Notably, we find a linear relationship in our setting: the stronger the correlation between persona variables and human annotations, the more accurate the LLM predictions are using persona prompting. In a zero-shot setting, a powerful 70b model with persona prompting captures 81% of the annotation variance achievable by linear regression trained on ground truth annotations. However, for most subjective NLP datasets, where persona variables have limited explanatory power, the benefits of persona prompting are limited.

Added

2026-09-30