EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bias of AI-generated content: an examination of news produced by large language models

Xiao Fang, Shangkun Che, Minjia Mao, Hongzhe Zhang, Ming Zhao, Xiaohang Zhao

Scientific Reports · 04.03.2024 · 14 (1)

DOI: 10.1038/s41598-024-55686-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scientific Reports, online erschienen am 04.03.2024. Verfasst von Xiao Fang und 5 weiteren Autor:innen. Beteiligte Einrichtung: University of Delaware, Newark, USA. xfang@udel.edu. Hauptthemen laut MEDLINE: Aortic Valve Insufficiency, Camelids, New World. Die Arbeit wurde bisher 173-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) have the potential to transform our lives and work through the content they generate, known as AI-Generated Content (AIGC). To harness this transformation, we need to understand the limitations of LLMs. Here, we investigate the bias of AIGC produced by seven representative LLMs, including ChatGPT and LLaMA. We collect news articles from The New York Times and Reuters, both known for their dedication to provide unbiased news. We then apply each examined LLM to generate news content with headlines of these news articles as prompts, and evaluate the gender and racial biases of the AIGC produced by the LLM by comparing the AIGC and the original news articles. We further analyze the gender bias of each LLM under biased prompts by adding gender-biased messages to prompts constructed from these news headlines. Our study reveals that the AIGC produced by each examined LLM demonstrates substantial gender and racial biases. Moreover, the AIGC generated by each LLM exhibits notable discrimination against females and individuals of the Black race. Among the LLMs, the AIGC generated by ChatGPT demonstrates the lowest level of bias, and ChatGPT is the sole model capable of declining content generation when provided with biased prompts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Aortic Valve InsufficiencyCamelids, New WorldHumansFemaleMaleAnimalsSexismBiasLanguage

Stichwörter der Autor:innen

AI-generated content (AIGC)BiasChatGPTGender biasGenerative AILarge language model (LLM)PromptRacial bias

Autor:innen und Institutionen

  • University of Delaware, Newark, USA. xfang@udel.edu.
  • Tsinghua University, Beijing, China. csk19@mails.tsinghua.edu.cn.
  • University of Delaware, Newark, USA.
  • Chinese University of Hong Kong, Shenzhen, China.
  • Shanghai University of Finance and Economics, Shanghai, China.

Zitieren

APA

Fang, X., Che, S., Mao, M., Zhang, H., Zhao, M., & Zhao, X. (2024). Bias of AI-generated content: an examination of news produced by large language models. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-55686-2

Vancouver

Fang X, Che S, Mao M, Zhang H, Zhao M, Zhao X. Bias of AI-generated content: an examination of news produced by large language models. Scientific Reports. 2024;14(1). doi:10.1038/s41598-024-55686-2

BibTeX
@article{Fang2024,
  author = {Fang, Xiao and Che, Shangkun and Mao, Minjia and Zhang, Hongzhe and Zhao, Ming and Zhao, Xiaohang},
  title = {Bias of AI-generated content: an examination of news produced by large language models},
  journal = {Scientific Reports},
  year = {2024},
  volume = {14},
  number = {1},
  doi = {10.1038/s41598-024-55686-2}
}
Kostenlos starten →