Saved in:
Bibliographic Details
Main Authors: Xie, Yutong, Mei, Qiaozhu, Yuan, Walter, Jackson, Matthew O.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.15752
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913922533031936
author Xie, Yutong
Mei, Qiaozhu
Yuan, Walter
Jackson, Matthew O.
author_facet Xie, Yutong
Mei, Qiaozhu
Yuan, Walter
Jackson, Matthew O.
contents By varying prompts to a large language model, we can elicit the full range of human behaviors in a variety of different scenarios in classic economic games. By analyzing which prompts elicit which behaviors, we can categorize and compare different strategic situations, which can also help provide insight into what different economic scenarios induce people to think about. We discuss how this provides a first step towards a non-standard method of inferring (deciphering) the motivations behind the human behaviors. We also show how this deciphering process can be used to categorize differences in the behavioral tendencies of different populations.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15752
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Using Large Language Models to Categorize Strategic Situations and Decipher Motivations Behind Human Behaviors
Xie, Yutong
Mei, Qiaozhu
Yuan, Walter
Jackson, Matthew O.
Artificial Intelligence
By varying prompts to a large language model, we can elicit the full range of human behaviors in a variety of different scenarios in classic economic games. By analyzing which prompts elicit which behaviors, we can categorize and compare different strategic situations, which can also help provide insight into what different economic scenarios induce people to think about. We discuss how this provides a first step towards a non-standard method of inferring (deciphering) the motivations behind the human behaviors. We also show how this deciphering process can be used to categorize differences in the behavioral tendencies of different populations.
title Using Large Language Models to Categorize Strategic Situations and Decipher Motivations Behind Human Behaviors
topic Artificial Intelligence
url https://arxiv.org/abs/2503.15752