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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11620%2F25%3A10508489" target="_blank" >RIV/00216208:11620/25:10508489 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=..Xy-q6SzJ" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=..Xy-q6SzJ</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1073/pnas.2415697122" target="_blank" >10.1073/pnas.2415697122</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10700 - Other natural sciences

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Proceedings of the National Academy of Sciences of the United States of America

ISSN

0027-8424

e-ISSN

1091-6490

Svazek periodika

122

Číslo periodika v rámci svazku

31

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

8

Strana od-do

e2415697122

Kód UT WoS článku

001547028700001

EID výsledku v databázi Scopus

2-s2.0-105012649316