Saved in:
Bibliographic Details
Main Authors: Wang, Yue, Wei, Liesheng, Wang, Yuxiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.11933
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915448102060032
author Wang, Yue
Wei, Liesheng
Wang, Yuxiang
author_facet Wang, Yue
Wei, Liesheng
Wang, Yuxiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11933
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detection
Wang, Yue
Wei, Liesheng
Wang, Yuxiang
Computation and Language
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.
title CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detection
topic Computation and Language
url https://arxiv.org/abs/2508.11933