PuSH - Publikationsserver des Helmholtz Zentrums München

Hussain, Z.* ; Binz, M. ; Mata, R.* ; Wulff, D.U.*

A tutorial on open-source large language models for behavioral science.

Behav. Res. Methods, DOI: 10.3758/s13428-024-02455-8 (2024)
Verlagsversion DOI PMC
Open Access Gold (Paid Option)
Creative Commons Lizenzvertrag
Large language models (LLMs) have the potential to revolutionize behavioral science by accelerating and improving the research cycle, from conceptualization to data analysis. Unlike closed-source solutions, open-source frameworks for LLMs can enable transparency, reproducibility, and adherence to data protection standards, which gives them a crucial advantage for use in behavioral science. To help researchers harness the promise of LLMs, this tutorial offers a primer on the open-source Hugging Face ecosystem and demonstrates several applications that advance conceptual and empirical work in behavioral science, including feature extraction, fine-tuning of models for prediction, and generation of behavioral responses. Executable code is made available at github.com/Zak-Hussain/LLM4BeSci.git . Finally, the tutorial discusses challenges faced by research with (open-source) LLMs related to interpretability and safety and offers a perspective on future research at the intersection of language modeling and behavioral science.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Korrespondenzautor
Schlagwörter Behavioral Science ; Hugging Face ; Large Language Models; Cognitive Reflection; Ai
ISSN (print) / ISBN 1554-351X
e-ISSN 1554-3528
Zeitschrift Behavior research methods
Verlag Springer
Verlagsort One New York Plaza, Suite 4600, New York, Ny, United States
Nichtpatentliteratur Publikationen
Institut(e) Institute of AI for Health (AIH)
Förderungen Academy of Finland (AKA)
Swiss Science Foundation
Schweizerischer Nationalfonds zur Frderung der Wissenschaftlichen Forschung