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...

Studies analysing land managers' stated preferences for participation in environmental policy initiatives have largely overlooked the issue of hypothetical bias (HB). In this study, a discrete choice experiment focusing on farmers' willingness to accept (WTA) to participate in agri-environmental...

Models derived from random utility theory represent the workhorse methods to learn about consumer preferences from discrete choice data. However, a large body of literature documents various behavioral patterns that cannot be captured by basic random utility models and require different...