Collaborative Evaluation of Deepfake Text with Deliberation-Enhancing Dialogue Systems
This addresses the challenge of distinguishing deepfake content for users relying on collaborative detection, but it is incremental as it builds on existing group-based methods with a chatbot enhancement.
The study tackled the problem of detecting deepfake text by exploring a deliberation-enhancing chatbot to support group efforts, finding that group-based problem-solving significantly improved accuracy compared to individual efforts, though the chatbot did not substantially boost performance overall.
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.