Revealing Life Preferences Through LLMs (NBER Working Paper 35185)

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.

The authors' own abstract, copied from nber.org.

How to cite it

Built from the details listed on this page. Check them against the paper before you submit.

Haq, O. A., Chandra, A., & Jagelka, T. (2026). Revealing Life Preferences Through LLMs (NBER Working Paper 35185). NBER Working Paper 35185. https://www.nber.org/papers/w35185

Haq, Omar Abdel, et al. "Revealing Life Preferences Through LLMs (NBER Working Paper 35185)." NBER Working Paper 35185, 2026, https://www.nber.org/papers/w35185.

@article{haq2026revealing,
  title = {Revealing Life Preferences Through LLMs (NBER Working Paper 35185)},
  author = {Omar Abdel Haq and Amitabh Chandra and Tomáš Jagelka},
  journal = {NBER Working Paper 35185},
  year = {2026},
  url = {https://www.nber.org/papers/w35185},
}

What it is

Omar Abdel Haq, Amitabh Chandra, Tomáš Jagelka and co-authors use large language models to elicit and measure people's life preferences and trade-offs (May 2026).

Topics