DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature

Understand

The increasing fluency and widespread usage of large language models (LLMs) highlight the desirability of corresponding tools aiding detection of LLM-generated text.

• In this paper, we identify a property of the structure of an LLM's probability function that is useful for such detection.
• Specifically, we demonstrate that text sampled from an LLM tends to occupy negative curvature regions of the model's log probability function.
• Leveraging this observation, we then define a new curvature-based criterion for judging if a passage is generated from a given LLM.