DiSCoKit: An open-source toolkit for deploying live LLM experiences in survey research
PLOS One · 31.07.2026 · 21 (7) · e0354904
DOI: 10.1371/journal.pone.0354904 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 31.07.2026. Verfasst von Jaime Banks und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Studies, Syracuse University, Syracuse, New York, United States of America. Hauptthemen laut MEDLINE: Large Language Models, Software, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Army Research Office, Alfred P. Sloan Foundation.
Abstract (Originalsprache)
In scientific studies of human-AI interaction dynamics, researchers often need to present participants with opportunities to interact with live large-language models (LLMs). However, technical and practical challenges (from survey platform limitations and logging chat data to manipulating AI behaviors for experimental designs) often inhibit survey-based deployment of AI stimuli. We developed DiSCoKit—an open-source toolkit for deploying live LLM experiences (e.g., ones based on models delivered through Microsoft Azure portal) through JavaScript-enabled survey platforms (e.g., Qualtrics). We describe the toolkit’s scientific motivation, architecture, and operation. We also offer an example of toolkit deployment and customization, along with discussing its possibilities and limitations. Altogether, DiSCoKit gives researchers a flexible, secure, scalable solution for deploying naturalistic LLM stimulus experiences through online surveys.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Information Studies, Syracuse University, Syracuse, New York, United States of America.
- Department of Physics, Syracuse University, Syracuse, New York, United States of America.
- Open Source Program Office, Syracuse University, Syracuse, New York, United States of America.
ORCID-Profile: Jaime Banks
Förderung
- Army Research Office
- Alfred P. Sloan Foundation
Zitieren
APA
Banks, J., Stromer-Galley, J., Singh, S., & Capano, C. (2026). DiSCoKit: An open-source toolkit for deploying live LLM experiences in survey research. PLOS One, 21(7), e0354904. https://doi.org/10.1371/journal.pone.0354904
Vancouver
Banks J, Stromer-Galley J, Singh S, Capano C. DiSCoKit: An open-source toolkit for deploying live LLM experiences in survey research. PLOS One. 2026;21(7):e0354904. doi:10.1371/journal.pone.0354904
BibTeX
@article{Banks2026,
author = {Banks, Jaime and Stromer-Galley, Jonathan and Singh, Samiksha and Capano, Collin},
title = {DiSCoKit: An open-source toolkit for deploying live LLM experiences in survey research},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {7},
pages = {e0354904},
doi = {10.1371/journal.pone.0354904}
}
EUVIMED