Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
This work addresses the urgent need for reliable detection of AI-generated content, which is crucial for combating misinformation and ensuring academic integrity, though it appears incremental as it builds on existing rewrite-based methods.
The paper tackles the problem of detecting LLM-generated text to address misinformation and academic integrity concerns, introducing a rewrite-based detection algorithm that learns adaptive distances between original and rewritten text, achieving relative improvements from 54.3% to 75.4% over baselines across different LLMs.
Modern large language models (LLMs) such as GPT, Claude, and Gemini have transformed the way we learn, work, and communicate. Yet, their ability to produce highly human-like text raises serious concerns about misinformation and academic integrity, making it an urgent need for reliable algorithms to detect LLM-generated content. In this paper, we start by presenting a geometric approach to demystify rewrite-based detection algorithms, revealing their underlying rationale and demonstrating their generalization ability. Building on this insight, we introduce a novel rewrite-based detection algorithm that adaptively learns the distance between the original and rewritten text. Theoretically, we demonstrate that employing an adaptively learned distance function is more effective for detection than using a fixed distance. Empirically, we conduct extensive experiments with over 100 settings, and find that our approach demonstrates superior performance over baseline algorithms in the majority of scenarios. In particular, it achieves relative improvements from 54.3% to 75.4% over the strongest baseline across different target LLMs (e.g., GPT, Claude, and Gemini). A python implementation of our proposal is publicly available at https://github.com/Mamba413/L2D.