Detecting text generated by modern large language models is thought to be hard, as both LLMs and humans can exhibit a wide range of complex behaviors. However, we find that a score based on contrasting two closely related language models is highly accurate at separating human-generated and machine-generated text. Based on this mechanism, we propose a novel LLM detector that only requires simple calculations using a pair of pre-trained LLMs. The method, called Binoculars, achieves state-of-the-art accuracy without any training data. It is capable of spotting machine text from a range of modern LLMs without any model-specific modifications. We comprehensively evaluate Binoculars on a number of text sources and in varied situations. Over a wide range of document types, Binoculars detects over 90% of generated samples from ChatGPT (and other LLMs) at a false positive rate of 0.01%, despite not being trained on any ChatGPT data.
@article{arxiv.2401.12070,
title = {Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text},
author = {Abhimanyu Hans and Avi Schwarzschild and Valeriia Cherepanova and Hamid Kazemi and Aniruddha Saha and Micah Goldblum and Jonas Geiping and Tom Goldstein},
journal= {arXiv preprint arXiv:2401.12070},
year = {2024}
}
Comments
20 pages, code available at https://github.com/ahans30/Binoculars