EUVIMEDEUVIMED entdecken
Crossref

Stochastic lies: How LLM-powered chatbots deal with Russian disinformation about the war in Ukraine

Mykola Makhortykh, Maryna Sydorova, Ani Baghumyan, Victoria Vziatysheva, Elizaveta Kuznetsova

Harvard Kennedy School Misinformation Review · 26.08.2024

DOI: 10.37016/mr-2020-154 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Harvard Kennedy School Misinformation Review, online erschienen am 26.08.2024. Verfasst von Mykola Makhortykh und 4 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: Bundesministerium für Bildung und Forschung.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Research on digital misinformation has turned its attention to large language models (LLMs) and their handling of sensitive political topics. Through an AI audit, we analyze how three LLM-powered chatbots (Perplexity, Google Bard, and Bing Chat) generate content in response to the prompts linked to common Russian disinformation narratives about the war in Ukraine. We find major differences between chatbots in the accuracy of outputs and the integration of statements debunking Russian disinformation claims related to prompts’ topics. Moreover, we show that chatbot outputs are subject to substantive variation, which can result in random user exposure to false information.

Förderung

  • Bundesministerium für Bildung und Forschung

Zitieren

APA

Makhortykh, M., Sydorova, M., Baghumyan, A., Vziatysheva, V., & Kuznetsova, E. (2024). Stochastic lies: How LLM-powered chatbots deal with Russian disinformation about the war in Ukraine. Harvard Kennedy School Misinformation Review. https://doi.org/10.37016/mr-2020-154

Vancouver

Makhortykh M, Sydorova M, Baghumyan A, Vziatysheva V, Kuznetsova E. Stochastic lies: How LLM-powered chatbots deal with Russian disinformation about the war in Ukraine. Harvard Kennedy School Misinformation Review. 2024. doi:10.37016/mr-2020-154

BibTeX
@article{Makhortykh2024,
  author = {Makhortykh, Mykola and Sydorova, Maryna and Baghumyan, Ani and Vziatysheva, Victoria and Kuznetsova, Elizaveta},
  title = {Stochastic lies: How LLM-powered chatbots deal with Russian disinformation about the war in Ukraine},
  journal = {Harvard Kennedy School Misinformation Review},
  year = {2024},
  doi = {10.37016/mr-2020-154}
}
Kostenlos starten →