2026-02-26 ペンシルベニア州立大学
People may be more willing to interact with AI-powered chatbots that represent a particular sociodemographic background, but current bots don’t represent people from some backgrounds well, according to researchers from the College of Information Sciences and Technology. Credit: Cole Handerhan / Penn State. Creative Commons
＜関連情報＞
- https://www.psu.edu/news/information-sciences-and-technology/story/chatbots-overemphasize-sociodemographic-stereotypes
- https://arxiv.org/abs/2505.07850
二つのアイデンティティの物語：人間とAIが作成したペルソナの倫理的監査 A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas
Pranav Narayanan Venkit, Jiayi Li, Yingfan Zhou, Sarah Rajtmajer, Shomir Wilson
arXiv Submitted on 7 May 2025
DOI:https://doi.org/10.48550/arXiv.2505.07850
Abstract
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.
