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

• URL: http://arxiv.org/abs/2301.11305v2
• Date: Sun, 23 Jul 2023 04:18:36 GMT
• Title: DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
• Authors: Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D. Manning, Chelsea Finn
• Abstract summary: We show that text sampled from an large language model tends to occupy negative curvature regions of the model's log probability function. We then define a new curvature-based criterion for judging if a passage is generated from a given LLM. We find DetectGPT is more discriminative than existing zero-shot methods for model sample detection.
• Score: 143.5381108333212
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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. This approach, which we call DetectGPT, does not require training a separate classifier, collecting a dataset of real or generated passages, or explicitly watermarking generated text. It uses only log probabilities computed by the model of interest and random perturbations of the passage from another generic pre-trained language model (e.g., T5). We find DetectGPT is more discriminative than existing zero-shot methods for model sample detection, notably improving detection of fake news articles generated by 20B parameter GPT-NeoX from 0.81 AUROC for the strongest zero-shot baseline to 0.95 AUROC for DetectGPT. See https://ericmitchell.ai/detectgpt for code, data, and other project information.

Related papers

• Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness [6.229124658686219]
  We develop a generic dual-channel detection paradigm that uses token cohesiveness as a plug-and-play module to improve existing zero-shot detectors. To calculate token cohesiveness, we use a few rounds of random token deletion and semantic difference measurement. Experiments with four state-of-the-art base detectors on various datasets, source models, and evaluation settings demonstrate the effectiveness and generality of the proposed approach.
  arXiv  Detail & Related papers  (2024-09-25T13:18:57Z)
• Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method [108.56493934296687]
  We introduce a divergence-based calibration method, inspired by the divergence-from-randomness concept, to calibrate token probabilities for pretraining data detection. We have developed a Chinese-language benchmark, PatentMIA, to assess the performance of detection approaches for LLMs on Chinese text.
  arXiv  Detail & Related papers  (2024-09-23T07:55:35Z)
• Applying Ensemble Methods to Model-Agnostic Machine-Generated Text Detection [0.0]
  We study the problem of detecting machine-generated text when the large language model it is possibly derived from is unknown. We use a zero-shot model for machine-generated text detection which is highly accurate when the generative (or base) language model is the same as the discriminative (or scoring) language model.
  arXiv  Detail & Related papers  (2024-06-18T12:58:01Z)
• Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore [51.65730053591696]
  We propose a simple but effective black-box zero-shot detection approach. It is predicated on the observation that human-written texts typically contain more grammatical errors than LLM-generated texts. Our method achieves an average AUROC of 98.7% and shows strong robustness against paraphrase and adversarial perturbation attacks.
  arXiv  Detail & Related papers  (2024-05-07T12:57:01Z)
• Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature [36.31281981509264]
  Large language models (LLMs) have shown the ability to produce fluent and cogent content. To build trustworthy AI systems, it is imperative to distinguish between machine-generated and human-authored content. Fast-DetectGPT is an optimized zero-shot detector that substitutes DetectGPT's perturbation step with a more efficient sampling step.
  arXiv  Detail & Related papers  (2023-10-08T11:41:28Z)
• Zero-Shot Detection of Machine-Generated Codes [83.0342513054389]
  This work proposes a training-free approach for the detection of LLMs-generated codes. We find that existing training-based or zero-shot text detectors are ineffective in detecting code. Our method exhibits robustness against revision attacks and generalizes well to Java codes.
  arXiv  Detail & Related papers  (2023-10-08T10:08:21Z)
• Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model [14.98695074168234]
  We propose a new method to detect machine-generated text, especially from large language models (LLMs) We use a Bayesian surrogate model, which allows us to select typical samples based on Bayesian uncertainty and interpolate scores from typical samples to other samples, to improve query efficiency. Empirical results demonstrate that our method significantly outperforms existing approaches under a low query budget.
  arXiv  Detail & Related papers  (2023-05-26T04:23:10Z)
• DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection [56.513637720967566]
  Large language models (LLMs) can generate texts that pose risks of misuse, such as plagiarism, planting fake reviews on e-commerce platforms, or creating inflammatory false tweets. Existing high-quality detection methods usually require access to the interior of the model to extract the intrinsic characteristics. We propose to extract deep intrinsic characteristics of the black-box model generated texts.
  arXiv  Detail & Related papers  (2023-05-21T17:26:16Z)
• Smaller Language Models are Better Black-box Machine-Generated Text Detectors [56.36291277897995]
  Small and partially-trained models are better universal text detectors. We find that whether the detector and generator were trained on the same data is not critically important to the detection success. For instance, the OPT-125M model has an AUC of 0.81 in detecting ChatGPT generations, whereas a larger model from the GPT family, GPTJ-6B, has AUC of 0.45.
  arXiv  Detail & Related papers  (2023-05-17T00:09:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.