Integrating machine behavior into human subject experiments: A user-friendly toolkit and illustrations
Large Language Models (LLMs) have the potential to profoundly transform and enrich experimental economic research. We propose a new software framework, "alter_ego", which makes it easy to design experiments between LLMs and to integrate LLMs into oTreebased experiments with human subjects. Our toolkit is freely available at github.com/mrpg/ego. To illustrate, we run differently framed prisoner's dilemmas with interacting machines as well as with humanmachine interaction. Framing effects in machine-only treatments are strong and similar to those expected from previous human-only experiments, yet less pronounced and qualitatively different if machines interact with human participants.
Year of publication: |
2024
|
---|---|
Authors: | Engel, Christoph ; Grossmann, Max R. P. ; Ockenfels, Axel |
Publisher: |
Bonn and Cologne : University of Bonn and University of Cologne, Reinhard Selten Institute (RSI) |
Subject: | Software for experiments | large language models | human-machine interaction | framing |
Saved in:
freely available
Series: | |
---|---|
Type of publication: | Book / Working Paper |
Type of publication (narrower categories): | Working Paper |
Language: | English |
Other identifiers: | 1889864730 [GVK] |
Classification: | C91 - Laboratory, Individual Behavior ; C92 - Laboratory; Group Behavior ; D91 - Intertemporal Consumer Choice; Life Cycle Models and Saving ; O33 - Technological Change: Choices and Consequences; Diffusion Processes ; L86 - Information and Internet Services; Computer Software |
Source: |
Persistent link: https://www.econbiz.de/10014536319