Automated Social Science: Language Models as Scientist and Subjects

We present an approach for automatically generating and testing, in silico, social scientific hypotheses. This automation is made possible by recent advances in large language models (LLM), but the key feature of the approach is the use of structural causal models. Structural causal models provide a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	NBER Working Paper Series
Hauptverfasser:	Manning, Benjamin S, Zhu, Kehang, Horton, John J
Format:	Paper
Sprache:	Englisch
Veröffentlicht:	Cambridge National Bureau of Economic Research, Inc 01.04.2024
Schlagworte:	Automation Computer simulation Hypotheses Language Large language models
ISSN:	0898-2937
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!