EMMM, Explain Me My Model! Explainable Machine Generated Text Detection in Dialogues
This addresses the need for trustworthy AI in customer service by improving interpretability for non-expert operators, though it is incremental as it builds on existing detection methods.
The paper tackles the problem of detecting machine-generated text in customer service dialogues to prevent user impersonation, proposing EMMM, which provides explanations accessible to non-expert users with 70% preference from evaluators while achieving competitive accuracy and low latency under 1 second.
The rapid adoption of large language models (LLMs) in customer service introduces new risks, as malicious actors can exploit them to conduct large-scale user impersonation through machine-generated text (MGT). Current MGT detection methods often struggle in online conversational settings, reducing the reliability and interpretability essential for trustworthy AI deployment. In customer service scenarios where operators are typically non-expert users, explanation become crucial for trustworthy MGT detection. In this paper, we propose EMMM, an explanation-then-detection framework that balances latency, accuracy, and non-expert-oriented interpretability. Experimental results demonstrate that EMMM provides explanations accessible to non-expert users, with 70\% of human evaluators preferring its outputs, while achieving competitive accuracy compared to state-of-the-art models and maintaining low latency, generating outputs within 1 second. Our code and dataset are open-sourced at https://github.com/AngieYYF/EMMM-explainable-chatbot-detection.