CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detection

TL;DR

CAMF is a novel multi-agent framework that improves machine-generated text detection by analyzing linguistic features and inconsistencies across multiple dimensions using adversarial collaboration.

Contribution

Introduces CAMF, a multi-agent adversarial framework that enhances detection of machine-generated text through multi-dimensional analysis and collaborative judgment.

Findings

CAMF outperforms existing zero-shot detection methods.

Deep analysis of linguistic inconsistencies improves detection accuracy.

Framework effectively identifies subtle cues of machine-generated text.

Abstract

Detecting machine-generated text (MGT) from contemporary Large Language Models (LLMs) is increasingly crucial amid risks like disinformation and threats to academic integrity. Existing zero-shot detection paradigms, despite their practicality, often exhibit significant deficiencies. Key challenges include: (1) superficial analyses focused on limited textual attributes, and (2) a lack of investigation into consistency across linguistic dimensions such as style, semantics, and logic. To address these challenges, we introduce the \textbf{C}ollaborative \textbf{A}dversarial \textbf{M}ulti-agent \textbf{F}ramework (\textbf{CAMF}), a novel architecture using multiple LLM-based agents. CAMF employs specialized agents in a synergistic three-phase process: \emph{Multi-dimensional Linguistic Feature Extraction}, \emph{Adversarial Consistency Probing}, and \emph{Synthesized Judgment Aggregation}. This structured collaborative-adversarial process enables a deep analysis of subtle, cross-dimensional textual incongruities indicative of non-human origin. Empirical evaluations demonstrate CAMF's significant superiority over state-of-the-art zero-shot MGT detection techniques.