Collaborative Evaluation of Deepfake Text with Deliberation-Enhancing Dialogue Systems

2025-03-06

AI Summary

This study addresses the challenge of human-AI collaborative detection of generative-AI–forged text (deepfake text). We propose and evaluate DeepFakeDeLiBot, a negotiation-augmented dialogue system that—uniquely for group-level detection—integrates real-time guidance, collaborative behavior modeling, and multi-turn reasoning prompts. Our experiments reveal that group dynamic quality—specifically consensus level and reasoning diversity—predicts detection efficacy more reliably than individual accuracy; group collaboration substantially outperforms individual detection; and while DeepFakeDeLiBot does not increase overall accuracy, it significantly enhances participant engagement, accelerates consensus formation, and increases both the frequency and diversity of reasoning-oriented utterances. This work establishes a novel paradigm for deepfake text detection centered on optimizing collective cognitive processes rather than isolated model performance.

Technology Category

• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-AI Collaboration / Human-AI Teaming
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

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. extit{Dataset and source code used in this study will be made publicly available upon acceptance of the manuscript.

Problem

• Challenges in distinguishing authentic from deepfake text
• Effectiveness of group-based deepfake text detection
• Role of AI chatbots in enhancing group deliberation dynamics

Innovation

• Deliberation-enhancing chatbot for deepfake detection
• Group-based problem-solving improves detection accuracy
• Chatbot enhances group dynamics and participant engagement