Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better

The burgeoning generative capabilities of large language models (LLMs) have raised growing concerns about abuse, demanding automatic machine-generated text detectors. De-tectGPT (Mitchell et al., 2023), a zero-shot metric-based detector, first introduces perturbation and shows great performance improvement. However, in DetectGPT, the random perturbation strategy could introduce noise, and logit regression depends on the threshold, harming the generalizability and applicability of individual or small-batch inputs. Hence, we propose a novel fine-tuned detector, PECOLA, bridging metric-based and fine-tuned methods by contrastive learning on selective perturbation. Selective strategy retains important tokens during perturbation and weights for multi-pair contrastive learning. The experiments show that PECOLA outperforms the state-of-the-art (SOTA) by 1.20% in accuracy on average on four public datasets. And we further analyze the effectiveness, robustness, and generalization of the method. 1 * Corresponding author 1 The code and datasets are released at https://github. com/lsc-1/Pecola . Original Connects to a specific sound, the ear is bone! You vibrate the bones of your jaw and that vibration travels into your ear. Sound doesn't just travel in air, it travels in all the other dimensions that connect people together. DetectGPT Connects to a specific sound, the connection is bone! You vibrate those bones of your jaw, and the vibration carries sound towards your ear. Sound doesn't just travel in air, it does travel in all materials.