Large language models (LLMs) as agents for augmented democracy

We explore an augmented democracy system built on off-the-shelf large language models (LLMs) fine-tuned to augment data on citizens' preferences elicited over policies extracted from the government programmes of the two main candidates of Brazil's 2022 presidential election. We use a train...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Philosophical transactions of the Royal Society of London. Series A: Mathematical, physical, and engineering sciences Jg. 382; H. 2285; S. 20240100
Hauptverfasser: Gudiño, Jairo F, Grandi, Umberto, Hidalgo, César
Format: Journal Article
Sprache:Englisch
Veröffentlicht: England 16.12.2024
Schlagworte:
Brazil
Democracy
Humans
Language
Models, Theoretical
Politics
Brazil
direct democracy
digital twins
algorithmic democracy
natural language processing
digital democracy
artificial intelligence
ISSN:1471-2962, 1471-2962
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We explore an augmented democracy system built on off-the-shelf large language models (LLMs) fine-tuned to augment data on citizens' preferences elicited over policies extracted from the government programmes of the two main candidates of Brazil's 2022 presidential election. We use a train-test cross-validation set-up to estimate the accuracy with which the LLMs predict both: a subject's individual political choices and the aggregate preferences of the full sample of participants. At the individual level, we find that LLMs predict out of sample preferences more accurately than a 'bundle rule', which would assume that citizens always vote for the proposals of the candidate aligned with their self-reported political orientation. At the population level, we show that a probabilistic sample augmented by an LLM provides a more accurate estimate of the aggregate preferences of a population than the non-augmented probabilistic sample alone. Together, these results indicate that policy preference data augmented using LLMs can capture nuances that transcend party lines and represents a promising avenue of research for data augmentation. This article is part of the theme issue 'Co-creating the future: participatory cities and digital governance'.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1471-2962
1471-2962
DOI:10.1098/rsta.2024.0100