Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917869162332160 |
|---|---|
| author | Bao, Guangsheng Zhao, Yanbin Teng, Zhiyang Yang, Linyi Zhang, Yue |
| author_facet | Bao, Guangsheng Zhao, Yanbin Teng, Zhiyang Yang, Linyi Zhang, Yue |
| contents | Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks. To build trustworthy AI systems, it is imperative to distinguish between machine-generated and human-authored content. The leading zero-shot detector, DetectGPT, showcases commendable performance but is marred by its intensive computational costs. In this paper, we introduce the concept of conditional probability curvature to elucidate discrepancies in word choices between LLMs and humans within a given context. Utilizing this curvature as a foundational metric, we present **Fast-DetectGPT**, an optimized zero-shot detector, which substitutes DetectGPT's perturbation step with a more efficient sampling step. Our evaluations on various datasets, source models, and test conditions indicate that Fast-DetectGPT not only surpasses DetectGPT by a relative around 75% in both the white-box and black-box settings but also accelerates the detection process by a factor of 340, as detailed in Table 1. See \url{https://github.com/baoguangsheng/fast-detect-gpt} for code, data, and results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_05130 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature Bao, Guangsheng Zhao, Yanbin Teng, Zhiyang Yang, Linyi Zhang, Yue Computation and Language Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks. To build trustworthy AI systems, it is imperative to distinguish between machine-generated and human-authored content. The leading zero-shot detector, DetectGPT, showcases commendable performance but is marred by its intensive computational costs. In this paper, we introduce the concept of conditional probability curvature to elucidate discrepancies in word choices between LLMs and humans within a given context. Utilizing this curvature as a foundational metric, we present **Fast-DetectGPT**, an optimized zero-shot detector, which substitutes DetectGPT's perturbation step with a more efficient sampling step. Our evaluations on various datasets, source models, and test conditions indicate that Fast-DetectGPT not only surpasses DetectGPT by a relative around 75% in both the white-box and black-box settings but also accelerates the detection process by a factor of 340, as detailed in Table 1. See \url{https://github.com/baoguangsheng/fast-detect-gpt} for code, data, and results. |
| title | Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2310.05130 |