Publications

Authors:

Bombieri, Marco; Rospocher, Marco

Title:

Mining Impersonification Bias in LLMs via Survey Filling

Year:

2025

Type of item:

Articolo in Rivista

Tipologia ANVUR:

Articolo su rivista

Language:

Inglese

Referee:

Sì

Name of journal:

INFORMATION

ISSN of journal:

2078-2489

N° Volume:

16

Number or Folder:

11

Page numbers:

1-21

Keyword:

large language models, personas, bias, stereotypes

Short description of contents:

In this paper, we introduce a survey-based methodology to audit LLM-generated personas by simulating 200 US residents and collecting responses to socio-demographic questions in a zero-shot setting. We investigate whether LLMs default to standardized profiles, how these profiles differ across models, and how conditioning on specific attributes affects the resulting portrayals. Our findings reveal that LLMs often produce homogenized personas that underrepresent demographic diversity and that conditioning on attributes such as gender, ethnicity, or disability may trigger stereotypical shifts. These results highlight implicit biases in LLMs and underscore the need for systematic approaches to evaluate and mitigate fairness risks in model outputs.

Web page:

https://www.mdpi.com/2078-2489/16/11/931

Product ID:

148137

Handle IRIS:

11562/1174028

Last Modified:

December 19, 2025

Bibliographic citation:

Bombieri, Marco; Rospocher, Marco, Mining Impersonification Bias in LLMs via Survey Filling «INFORMATION» , vol. 16 , n. 11 , 2025 , pp. 1-21

Consulta la scheda completa presente nel repository istituzionale della Ricerca di Ateneo