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.

利用两个紧密相关的预训练大型语言模型之间的对比得分，我们提出了一种新颖的仅需要使用这对 LLM 进行简单计算的 LLM 检测器，名为 Binoculars，它在不需要任何训练数据的情况下实现了最先进的准确性，能够在各种现代 LLM 的文本中发现机器生成的文本。在多种文档类型并且各个情况下，我们全面评估了 Binoculars 的性能，它以 0.01% 的误报率能够检测到 ChatGPT（和其他 LLM）生成的样本中超过 90% 的文本，尽管它没有接受任何 ChatGPT 数据的训练。