Predicting Human Choice Between Textually Described Lotteries
It addresses a gap in predicting real-world human choices for cognitive science, economics, and AI, though it is incremental by extending existing methods to textual data.
This study tackled the problem of predicting human decision-making between textually described lotteries, finding that fine-tuned LLMs like GPT-4o outperform hybrid models incorporating behavioral theory, with results highlighting fundamental differences from numerical settings.
Predicting human decision-making under risk and uncertainty is a long-standing challenge in cognitive science, economics, and AI. While prior research has focused on numerically described lotteries, real-world decisions often rely on textual descriptions. This study conducts the first large-scale exploration of human decision-making in such tasks using a large dataset of one-shot binary choices between textually described lotteries. We evaluate multiple computational approaches, including fine-tuning Large Language Models (LLMs), leveraging embeddings, and integrating behavioral theories of choice under risk. Our results show that fine-tuned LLMs, specifically GPT-4o, outperform hybrid models that incorporate behavioral theory, challenging established methods in numerical settings. These findings highlight fundamental differences in how textual and numerical information influence decision-making and underscore the need for new modeling strategies to bridge this gap.