Demographic Background Prompting Does Not Affect Linguistic Features on LLM-Generated News Texts

  1. Alberto Muñoz-Ortiz
  2. Carlos Gómez-Rodríguez 1
  3. David Vilares 1
  1. 1 Universidade da Coruña
    info
    Universidade da Coruña

    La Coruña, España

    ROR https://ror.org/01qckj285

    Localización xeográfica da organización Universidade da Coruña
Libro:
Proceedings XoveTIC 2024: Impulsando el talento científico
  1. Manuel Lagos Rodríguez (coord.)
  2. Tirso Varela Rodeiro (coord.)
  3. Javier Pereira Loureiro (coord.)
  4. Manuel Francisco González Penedo (coord.)

Editorial: Servizo de Publicacións ; Universidade da Coruña

Ano de publicación: 2024

Páxinas: 169-176

Tipo: Capítulo de libro

DIALNET GOOGLE SCHOLAR lock_openAcceso aberto editor

Resumo

We explored if implicit demographic information in prompts for large language models (LLMs) influences the linguistic features of generated text. Two LLMs were prompted to write news articles based on a title and summary, with prompts including demographic details like age, income, or nationality. The models were instructed not to explicitly reference these details. A total of 28,080 articles were generated by varying the demographics and topics. We calculated various linguistic metrics (e.g., sentence length, type-token ratio) and performed ANOVA, treating linguistic metrics as dependent variables and demographic categories as independent variables. Results indicate that demographic attributes do not significantly impact the linguistic metrics.

Fonte de datos: Dialnet