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

Kurzanzeige
dc.contributor.authorMakhortykh, Mykola
dc.contributor.authorSydorova, Maryna
dc.contributor.authorBaghumyan, A
dc.contributor.authorVziatysheva, Victoria
dc.contributor.authorKuznetsova, Elizaveta
dc.date.accessioned2025-03-31T13:51:14Z
dc.date.available2025-03-31T13:51:14Z
dc.date.collected2023-10
dc.date.issued2024
dc.description.abstractResearch 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.
dc.identifier.citationMakhortykh, 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 (HKS) Misinformation Review, 5(4). https://doi.org/10.37016/mr-2020-154
dc.identifier.doi10.37016/mr-2020-154
dc.identifier.urihttps://www.weizenbaum-library.de/handle/id/868
dc.language.isoeng
dc.rightsopen access
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectPerplexity
dc.subjectBing Chat
dc.subjectGoogle Bard
dc.subjectdisinformation
dc.subjectchatbot
dc.subjectRussisch-Ukrainischer Krieg
dc.titleStochastic lies: How LLM-powered chatbots deal with Russian disinformation about the war in Ukraine
dc.typeArticle
dc.type.statuspublishedVersion
dcmi.typeText
dcterms.bibliographicCitation.urlhttps://doi.org/10.37016/mr-2020-154
local.researchgroupPlattform-Algorithmen und digitale Propaganda
local.researchtopicDigitale Märkte und Öffentlichkeiten auf Plattformen
Dateien
Originalbündel
Gerade angezeigt 1 - 1 von 1
Vorschaubild
Name:
makhortykh-_stochastic-lies_20240826.pdf
Größe:
1.05 MB
Format:
Adobe Portable Document Format
Beschreibung:
Herunterladen
Sammlungen
Digitale Märkte und Öffentlichkeiten auf Plattformen
Aufsätze