Ghostbuster: Detecting Text Ghostwritten by Large Language Models

arXiv:2305.15047v3 Announce Type: replace
Abstract: We introduce Ghostbuster, a state-of-the-art system for detecting AI-generated text. Our method works by passing documents through a series of weaker language models, running a structured search over possible combinations of their features, and then training a classifier on the selected features to predict whether documents are AI-generated. Crucially, Ghostbuster does not require access to token probabilities from the target model, making it useful for detecting text generated by black-box models or unknown model versions. …

abstract ai-generated text art arxiv classifier cs.ai cs.cl documents features generated language language models large language large language models running search series state text through training type