# Using AI for User Representation: An Analysis of 83 Persona Prompts

arXiv: https://arxiv.org/abs/2508.13047 · HTML: https://mlsanity.com/paper/2508.13047/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 47 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Builds on (most cited first, 15 of 15)

- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [On the steerability of large language models toward data-driven personas](https://mlsanity.com/paper/2311.04978/) (2023)
- [When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models](https://mlsanity.com/paper/2311.10054/) (2023)
- [Writer-Defined AI Personas for On-Demand Feedback Generation](https://mlsanity.com/paper/2309.10433/) (2023)
- [IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering](https://mlsanity.com/paper/2408.13545/) (2024)
- [An Empathy-Based Sandbox Approach to Bridge the Privacy Gap among Attitudes, Goals, Knowledge, and Behaviors](https://mlsanity.com/paper/2309.14510/) (2023)
- [Persona-L has Entered the Chat: Leveraging LLM and Ability-based Framework for Personas of People with Complex Needs](https://mlsanity.com/paper/2409.15604/) (2024)
- [A Character-Centric Creative Story Generation via Imagination](https://mlsanity.com/paper/2409.16667/) (2024)
- [Improved prompting and process for writing user personas with LLMs, using qualitative interviews: Capturing behaviour and personality traits of users](https://mlsanity.com/paper/2310.06391/) (2023)
- [Conversational AI-Powered Design: ChatGPT as Designer, User, and Product](https://mlsanity.com/paper/2302.07406/) (2023)
- [Writing user personas with Large Language Models: Testing phase 6 of a Thematic Analysis of semi-structured interviews](https://mlsanity.com/paper/2305.18099/) (2023)
- [Evaluation of LLMs Biases Towards Elite Universities: A Persona-Based Exploration](https://mlsanity.com/paper/2407.12801/) (2024)
- [Why am I seeing this: Democratizing End User Auditing for Online Content Recommendations](https://mlsanity.com/paper/2410.04917/) (2024)
- [Creating and Evaluating Personas Using Generative AI: A Scoping Review of 81 Articles](https://mlsanity.com/paper/2504.04927/) (2025)
- [Persona Alchemy: Designing, Evaluating, and Implementing Psychologically-Grounded LLM Agents for Diverse Stakeholder Representation](https://mlsanity.com/paper/2505.18351/) (2025)

## Built on by (most cited first, 4 of 4)

- [Can AI Review Improve Paper Drafting? An Empirical Study on 20 Computer Architecture Submissions](https://mlsanity.com/paper/2606.01013/) (2026)
- [How to Model AI Agents as Personas?: Applying the Persona Ecosystem Playground to 41,300 Posts on Moltbook for Behavioral Insights](https://mlsanity.com/paper/2603.03140/) (2026)
- [PersonaCite: VoC-Grounded Interviewable Agentic Synthetic AI Personas for Verifiable User and Design Research](https://mlsanity.com/paper/2601.22288/) (2026)
- [Optimization and Constraint Modeling using LLMs with a Retrieval Augmented Generation Process](https://mlsanity.com/paper/2608.00015/) (2026)

## Abstract (arXiv)

We analyzed 83 persona prompts from 27 research articles that used large language models (LLMs) to generate user personas. Findings show that the prompts predominantly generate single personas. Several prompts express a desire for short or concise persona descriptions, which deviates from the tradition of creating rich, informative, and rounded persona profiles. Text is the most common format for generated persona attributes, followed by numbers. Text and numbers are often generated together, and demographic attributes are included in nearly all generated personas. Researchers use up to 12 prompts in a single study, though most research uses a small number of prompts. Comparison and testing multiple LLMs is rare. More than half of the prompts require the persona output in a structured format, such as JSON, and 74% of the prompts insert data or dynamic variables. We discuss the implications of increased use of computational personas for user representation.