Revealing Life Preferences Through LLMs

Omar Haq, Amitabh Chandra, Tomáš Jagelka, Erzo Luttmer and Joshua Schwartzstein

No 26134, RFBerlin Discussion Paper Series from ROCKWOOL Foundation Berlin (RFBerlin)

Abstract: Large Language Models (LLMs) are trained on a prodigious corpus of human writing and may reveal human preferences over characteristics of life courses, such as income, longevity, and working conditions. We present OpenAI's GPT-5.4 and a broadly representative sample of Americans with pairs of life stories and ask them to choose the life they would prefer for themselves. A person's choice is better predicted by the LLM's choice than by another person's choice over the same stories, and LLM valuations of several life attributes are similar to those derived from human responses. Our results suggest that LLM responses offer a scalable and cost-effective complement to existing methods for studying human preferences.

Keywords: Generative AI; preference estimation methods; choice experiments; survey validation (search for similar items in EconPapers)
JEL-codes: D0 H0 I0 (search for similar items in EconPapers)
Date: 2026-05
New Economics Papers: this item is included in nep-dcm
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.rfberlin.com/wp-content/uploads/2026/05/26134.pdf (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:crm:wpaper:26134

Access Statistics for this paper

More papers in RFBerlin Discussion Paper Series from ROCKWOOL Foundation Berlin (RFBerlin) Contact information at EDIRC.
Bibliographic data for series maintained by Moritz Lubczyk () and Matthew Nibloe ().