Collaborative Evaluation of Deepfake Text with Deliberation-Enhancing Dialogue Systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Jooyoung, Zhu, Xiaochen, Karadzhov, Georgi, Stafford, Tom, Vlachos, Andreas, Lee, Dongwon
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911541806235648
author Lee, Jooyoung
Zhu, Xiaochen
Karadzhov, Georgi
Stafford, Tom
Vlachos, Andreas
Lee, Dongwon
author_facet Lee, Jooyoung
Zhu, Xiaochen
Karadzhov, Georgi
Stafford, Tom
Vlachos, Andreas
Lee, Dongwon
contents The proliferation of generative models has presented significant challenges in distinguishing authentic human-authored content from deepfake content. Collaborative human efforts, augmented by AI tools, present a promising solution. In this study, we explore the potential of DeepFakeDeLiBot, a deliberation-enhancing chatbot, to support groups in detecting deepfake text. Our findings reveal that group-based problem-solving significantly improves the accuracy of identifying machine-generated paragraphs compared to individual efforts. While engagement with DeepFakeDeLiBot does not yield substantial performance gains overall, it enhances group dynamics by fostering greater participant engagement, consensus building, and the frequency and diversity of reasoning-based utterances. Additionally, participants with higher perceived effectiveness of group collaboration exhibited performance benefits from DeepFakeDeLiBot. These findings underscore the potential of deliberative chatbots in fostering interactive and productive group dynamics while ensuring accuracy in collaborative deepfake text detection. \textit{Dataset and source code used in this study will be made publicly available upon acceptance of the manuscript.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04945
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Collaborative Evaluation of Deepfake Text with Deliberation-Enhancing Dialogue Systems
Lee, Jooyoung
Zhu, Xiaochen
Karadzhov, Georgi
Stafford, Tom
Vlachos, Andreas
Lee, Dongwon
Computation and Language
Artificial Intelligence
Human-Computer Interaction
The proliferation of generative models has presented significant challenges in distinguishing authentic human-authored content from deepfake content. Collaborative human efforts, augmented by AI tools, present a promising solution. In this study, we explore the potential of DeepFakeDeLiBot, a deliberation-enhancing chatbot, to support groups in detecting deepfake text. Our findings reveal that group-based problem-solving significantly improves the accuracy of identifying machine-generated paragraphs compared to individual efforts. While engagement with DeepFakeDeLiBot does not yield substantial performance gains overall, it enhances group dynamics by fostering greater participant engagement, consensus building, and the frequency and diversity of reasoning-based utterances. Additionally, participants with higher perceived effectiveness of group collaboration exhibited performance benefits from DeepFakeDeLiBot. These findings underscore the potential of deliberative chatbots in fostering interactive and productive group dynamics while ensuring accuracy in collaborative deepfake text detection. \textit{Dataset and source code used in this study will be made publicly available upon acceptance of the manuscript.
title Collaborative Evaluation of Deepfake Text with Deliberation-Enhancing Dialogue Systems
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2503.04945