ToED: Tree of thoughts with Two-tier Prompts for Evading AI-Generated Text Detection

ACL ARR 2025 May Submission6606 Authors

Abstract:

AI-generated text (AIGT) detection evasion aims to reduce the detection probability of AIGT, helping to identify weaknesses in detectors and enhance their effectiveness and reliability in practical applications.
With the increasing demand for AIGT detection in recent years, evasion techniques have gradually become a prominent research focus.
Previous evasion methods have relied on manually crafted modification strategies, such as the selection of replacement words and hand-designed examples, which require expert domain knowledge.
To address the limitations of existing approaches, we propose the Tree of Evading Detection (ToED).
ToED employs a two-tier mixed prompt to construct a tree structure that guides LLMs in autonomously exploring optimal modification strategies, thereby enhancing the ability of AIGT to evade detection.
Experimental results demonstrate that our method effectively reduces the average detection accuracy of various AIGT detectors across texts generated by different LLMs, surpassing that of three other baselines and achieving the best performance in evading detection.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: security/privacy

Contribution Types: NLP engineering experiment

Languages Studied: English

Keywords: AI-generated text detection evasion, large language model

Submission Number: 6606