AI–AI bias: Large language models favor communications generated by large language models

Walter Laurito (), Benjamin Davis, Peli Grietzer, Tomáš GavenÄ Iak, Ada Böhm and Jan Kulveit ()
Additional contact information
Walter Laurito: a Information Process Engineering , Forschungszentrum Informatik , Karlsruhe 76131 , Germany
Benjamin Davis: b Private address , Andover , MA 04216
Peli Grietzer: c Arb Research , Prague 11636 , Czech Republic
Tomáš GavenÄ Iak: d Alignment of Complex Systems (ACS) Research Group , Center for Theoretical Studies , Charles University , Prague 110 00 , Czech Republic
Ada Böhm: d Alignment of Complex Systems (ACS) Research Group , Center for Theoretical Studies , Charles University , Prague 110 00 , Czech Republic
Jan Kulveit: d Alignment of Complex Systems (ACS) Research Group , Center for Theoretical Studies , Charles University , Prague 110 00 , Czech Republic

Proceedings of the National Academy of Sciences, 2025, vol. 122, issue 31, e2415697122

Abstract:

Are large language models (LLMs) biased in favor of communications produced by LLMs, leading to possible antihuman discrimination? Using a classical experimental design inspired by employment discrimination studies, we tested widely used LLMs, including GPT-3.5, GPT-4 and a selection of recent open-weight models in binary choice scenarios. These involved LLM-based assistants selecting between goods (the goods we study include consumer products, academic papers, and film-viewings) described either by humans or LLMs. Our results show a consistent tendency for LLM-based AIs to prefer LLM-presented options. This suggests the possibility of future AI systems implicitly discriminating against humans as a class, giving AI agents and AI-assisted humans an unfair advantage.

Keywords: AI bias; machine learning; artificial intelligence; large language models (LLMS) (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1073/pnas.2415697122 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nas:journl:v:122:y:2025:p:e2415697122

Access Statistics for this article

More articles in Proceedings of the National Academy of Sciences from Proceedings of the National Academy of Sciences
Bibliographic data for series maintained by PNAS Product Team ().