Perils and opportunities in using large language models in psychological research
PNAS Nexus · 28.06.2024 · 3 (7)
DOI: 10.1093/pnasnexus/pgae245 ↗Kurz gefasst
Fachartikel in der Zeitschrift PNAS Nexus, online erschienen am 16.07.2024. Verfasst von Suhaib Abdurahman und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, University of Southern California, Los Angeles, CA 90089, USA. Die Arbeit wurde bisher 116-mal zitiert (Crossref) und nennt 127 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DARPA INCAS, AFOSR.
Abstract (Originalsprache)
The emergence of large language models (LLMs) has sparked considerable interest in their potential application in psychological research, mainly as a model of the human psyche or as a general text-analysis tool. However, the trend of using LLMs without sufficient attention to their limitations and risks, which we rhetorically refer to as “GPTology”, can be detrimental given the easy access to models such as ChatGPT. Beyond existing general guidelines, we investigate the current limitations, ethical implications, and potential of LLMs specifically for psychological research, and show their concrete impact in various empirical studies. Our results highlight the importance of recognizing global psychological diversity, cautioning against treating LLMs (especially in zero-shot settings) as universal solutions for text analysis, and developing transparent, open methods to address LLMs’ opaque nature for reliable, reproducible, and robust inference from AI-generated data. Acknowledging LLMs’ utility for task automation, such as text annotation, or to expand our understanding of human psychology, we argue for diversifying human samples and expanding psychology’s methodological toolbox to promote an inclusive, generalizable science, countering homogenization, and over-reliance on LLMs.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Psychology, University of Southern California, Los Angeles, CA 90089, USA.
- Brain and Creativity Institute, University of Southern California, Los Angeles, CA 90089, USA.
- Department of Human Evolutionary Biology, Harvard University, Cambridge, MA 02138, USA.
- Department of Psychological and Brain Sciences, University of Massachusetts Amherst, Amherst, MA 01003, USA.
- Department of Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
- Department of Computer Science, University of Southern California, Los Angeles, CA 90089, USA.
ORCID-Profile: Suhaib Abdurahman, Mohammad Atari, Farzan Karimi-Malekabadi, Jackson Trager, Preni Golazizian, Ali Omrani, Morteza Dehghani
Förderung
- DARPA INCAS
- AFOSR
Zitieren
APA
Abdurahman, S., Atari, M., Karimi-Malekabadi, F., Xue, M. J., Trager, J., Park, P. S., Golazizian, P., Omrani, A., & Dehghani, M. (2024). Perils and opportunities in using large language models in psychological research. PNAS Nexus, 3(7). https://doi.org/10.1093/pnasnexus/pgae245
Vancouver
Abdurahman S, Atari M, Karimi-Malekabadi F, Xue MJ, Trager J, Park PS, et al. Perils and opportunities in using large language models in psychological research. PNAS Nexus. 2024;3(7). doi:10.1093/pnasnexus/pgae245
BibTeX
@article{Abdurahman2024,
author = {Abdurahman, Suhaib and Atari, Mohammad and Karimi-Malekabadi, Farzan and Xue, Mona J and Trager, Jackson and Park, Peter S and Golazizian, Preni and Omrani, Ali and Dehghani, Morteza},
title = {Perils and opportunities in using large language models in psychological research},
journal = {PNAS Nexus},
year = {2024},
volume = {3},
number = {7},
doi = {10.1093/pnasnexus/pgae245}
}
EUVIMED