A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909608469069824 |
|---|---|
| author | Venkit, Pranav Narayanan Li, Jiayi Zhou, Yingfan Rajtmajer, Sarah Wilson, Shomir |
| author_facet | Venkit, Pranav Narayanan Li, Jiayi Zhou, Yingfan Rajtmajer, Sarah Wilson, Shomir |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07850 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas Venkit, Pranav Narayanan Li, Jiayi Zhou, Yingfan Rajtmajer, Sarah Wilson, Shomir Computation and Language Artificial Intelligence Computers and Society 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. |
| title | A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2505.07850 |