LLM-Generated Text May Harm Your Retrieval! A Robust Detection Strategy for Retrieval-Augmented Generation
TL;DR
This paper explores the usage paradigms of LLM text detectors for RAG and highlights key limitations of off-the-shelf or directly fine-tuned detectors.
Abstract
Retrieval-augmented generation (RAG) effectively enhances the accuracy and timeliness of large language models (LLMs) by incorporating external knowledge retrieved from ex-ternal sources. However, with the increasing prevalence of LLM-generated content, exter-nal corpora used by RAG systems may become contaminated with LLM-generated texts. Such contamination compromises the reliability and quality of retrieved results, ultimately leading to a degradation in RAG performance, and raises concerns about the diminishing presence of human texts and the “Spiral of Silence” effect. A natural solution is to incorporate LLM text detectors into the RAG pipeline to filter out LLM-generated texts from the retrieved results. However, their effective use in RAG remains under-explored. In this paper, we explore the usage paradigms of LLM text detectors for RAG and highlight key limitations of off-the-shelf or directly fine-tuned detectors. To this end, we propose a RAG-aware data augmentation strategy that aligns detector training with realistic contamination patterns. Our approach synthesizes training data from both LLM and human texts under diverse generation modes. Experiments show that our method mit-igates performance degradation and improves the long-term stability of RAG systems.