SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text

The widespread adoption of <PRE_TAG>large language models (LLMs)</POST_TAG> has created an urgent need for robust tools to detect LLM-generated text, especially in light of <PRE_TAG>paraphrasing techniques</POST_TAG> that often evade existing detection methods. To address this challenge, we present a novel semantic-enhanced framework for detecting LLM-generated text (<PRE_TAG>SEFD</POST_TAG>) that leverages a <PRE_TAG>retrieval-based mechanism</POST_TAG> to fully utilize <PRE_TAG>text semantics</POST_TAG>. Our framework improves upon existing detection methods by systematically integrating <PRE_TAG>retrieval-based techniques</POST_TAG> with <PRE_TAG>traditional detectors</POST_TAG>, employing a carefully curated retrieval mechanism that strikes a balance between comprehensive coverage and computational efficiency. We showcase the effectiveness of our approach in sequential text scenarios common in real-world applications, such as <PRE_TAG>online forums</POST_TAG> and Q\&A platforms. Through comprehensive experiments across various LLM-generated texts and detection methods, we demonstrate that our framework substantially enhances detection accuracy in paraphrasing scenarios while maintaining robustness for standard LLM-generated content.