Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood
This addresses the challenge of detecting AI-generated text as models become more human-like, with potential applications in content moderation and authenticity verification.
The study tackled the problem of distinguishing human from model-generated text by using relative likelihood values and spectral features, achieving competitive performance with previous zero-shot methods and setting a new state-of-the-art for short-text detection.
Human and model-generated texts can be distinguished by examining the magnitude of likelihood in language. However, it is becoming increasingly difficult as language model's capabilities of generating human-like texts keep evolving. This study provides a new perspective by using the relative likelihood values instead of absolute ones, and extracting useful features from the spectrum-view of likelihood for the human-model text detection task. We propose a detection procedure with two classification methods, supervised and heuristic-based, respectively, which results in competitive performances with previous zero-shot detection methods and a new state-of-the-art on short-text detection. Our method can also reveal subtle differences between human and model languages, which find theoretical roots in psycholinguistics studies. Our code is available at https://github.com/CLCS-SUSTech/FourierGPT