# A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas

arXiv: https://arxiv.org/abs/2505.07850 · HTML: https://mlsanity.com/paper/2505.07850/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 72 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 20 of 20)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [On Measures of Biases and Harms in NLP](https://mlsanity.com/paper/2108.03362/) (2021)
- [A Complete Survey on LLM-based AI Chatbots](https://mlsanity.com/paper/2406.16937/) (2024)
- [AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia](https://mlsanity.com/paper/2305.11844/) (2023)
- [A Synthetic Dataset for Personal Attribute Inference](https://mlsanity.com/paper/2406.07217/) (2024)
- [Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans](https://mlsanity.com/paper/2401.08495/) (2024)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Building Better AI Agents: A Provocation on the Utilisation of Persona in LLM-based Conversational Agents](https://mlsanity.com/paper/2407.11977/) (2024)
- [Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach](https://mlsanity.com/paper/2407.14779/) (2024)
- [A Sociotechnical View of Algorithmic Fairness](https://mlsanity.com/paper/2110.09253/) (2021)
- [ChatGPT as Research Scientist: Probing GPT's Capabilities as a Research Librarian, Research Ethicist, Data Generator and Data Predictor](https://mlsanity.com/paper/2406.14765/) (2024)
- [From Melting Pots to Misrepresentations: Exploring Harms in Generative AI](https://mlsanity.com/paper/2403.10776/) (2024)
- [The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis](https://mlsanity.com/paper/2310.12318/) (2023)
- [Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations](https://mlsanity.com/paper/2504.13955/) (2025)
- [The Impostor is Among Us: Can Large Language Models Capture the Complexity of Human Personas?](https://mlsanity.com/paper/2501.04543/) (2025)
- [Concerns on Bias in Large Language Models when Creating Synthetic Personae](https://mlsanity.com/paper/2405.05080/) (2024)

## Built on by (most cited first, 8 of 8)

- [The Need for a Socially-Grounded Persona Framework for User Simulation](https://mlsanity.com/paper/2601.07110/) (2026)
- [One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization](https://mlsanity.com/paper/2601.18572/) (2026)
- [Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts](https://mlsanity.com/paper/2602.03545/) (2026)
- [Measuring Lexical Diversity of Synthetic Data Generated through Fine-Grained Persona Prompting](https://mlsanity.com/paper/2505.17390/) (2025)
- [What if AI systems weren't chatbots?](https://mlsanity.com/paper/2605.07896/) (2026)
- [PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI](https://mlsanity.com/paper/2605.05682/) (2026)
- [On Defining Erasure Harms for NLP](https://mlsanity.com/paper/2606.15815/) (2026)
- [Who Should Be Generated? Justifying Demographic Targets in Open-Ended Generation](https://mlsanity.com/paper/2608.02551/) (2026)

## Abstract (arXiv)

As LLMs (large language models) are increasingly used to generate synthetic personas particularly in data-limited domains such as health, privacy, and HCI, it becomes necessary to understand how these narratives represent identity, especially that of minority communities. In this paper, we audit synthetic personas generated by 3 LLMs (GPT4o, Gemini 1.5 Pro, Deepseek 2.5) through the lens of representational harm, focusing specifically on racial identity. Using a mixed methods approach combining close reading, lexical analysis, and a parameterized creativity framework, we compare 1512 LLM generated personas to human-authored responses. Our findings reveal that LLMs disproportionately foreground racial markers, overproduce culturally coded language, and construct personas that are syntactically elaborate yet narratively reductive. These patterns result in a range of sociotechnical harms, including stereotyping, exoticism, erasure, and benevolent bias, that are often obfuscated by superficially positive narrations. We formalize this phenomenon as algorithmic othering, where minoritized identities are rendered hypervisible but less authentic. Based on these findings, we offer design recommendations for narrative-aware evaluation metrics and community-centered validation protocols for synthetic identity generation.