Aldog12/MAGE

--- license: apache-2.0 --- <div align="center"> <h1>MAGE: Machine-generated Text Detection in the Wild</h1> </div> ## 🚀 Introduction Recent advances in large language models have enabled them to reach a level of text generation comparable to that of humans. These models show powerful capabilities across a wide range of content, including news article writing, story generation, and scientific writing. Such capability further narrows the gap between human-authored and machine-generated texts, highlighting the importance of machine-generated text detection to avoid potential risks such as fake news propagation and plagiarism. In practical scenarios, the detector faces texts from various domains or LLMs without knowing their sources. To this end, we build **a comprehensive testbed for machine-generated text detection**, by gathering texts from various human writings and machine-generated texts generated by different LLMs. The data in this repository is used to evaluate the effectiveness of machine-generated detection methods, as described in our paper titled "MAGE: Machine-generated Text Detection in the Wild" (available at https://arxiv.org/abs/2305.13242). We invite you to test your own detection methods on our testbed and encourage you to star our [Github repo](https://github.com/yafuly/MAGE). ## 📚 Citation If you use this dataset in your research, please cite it as follows: ```bibtex @misc{li2024mage, title={MAGE: Machine-generated Text Detection in the Wild}, author={Yafu Li and Qintong Li and Leyang Cui and Wei Bi and Zhilin Wang and Longyue Wang and Linyi Yang and Shuming Shi and Yue Zhang}, year={2024}, eprint={2305.13242}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` We welcome contributions to improve this dataset! If you have any questions or feedback, please feel free to reach out at [e-mail]. <!-- # 🤝 Contributing -->license: apache-2.0 --- <div align="center"> <h1>MAGE：野外场景下的机器生成文本检测</h1> </div> ## 🚀 简介 近年来，大语言模型（LLM）的技术进展使其文本生成能力达到了可与人类媲美的水平。此类模型在诸多内容生成场景中展现出强大能力，涵盖新闻撰稿、故事创作与学术写作等领域。这类能力进一步缩小了人类原创文本与机器生成文本之间的差距，凸显了机器生成文本检测技术的重要性，以规避假新闻传播、学术抄袭等潜在风险。在实际应用场景中，检测工具往往需要面对来自不同领域、由未知LLM生成的文本。 为此，我们收集了各类人类原创文本与不同LLM生成的机器生成文本，构建了**一套面向机器生成文本检测的综合测试基准平台**。本仓库中的数据可用于评估机器生成文本检测方法的有效性，相关细节可参见我们题为《MAGE：野外场景下的机器生成文本检测》的论文（链接：https://arxiv.org/abs/2305.13242）。我们诚挚邀请各位研究者在本测试基准上测试自主研发的检测方法，并欢迎为我们的[GitHub仓库](https://github.com/yafuly/MAGE)点亮Star。 ## 📚 引用 若您在研究中使用本数据集，请按照以下格式引用： bibtex @misc{li2024mage, title={MAGE: Machine-generated Text Detection in the Wild}, author={Yafu Li and Qintong Li and Leyang Cui and Wei Bi and Zhilin Wang and Longyue Wang and Linyi Yang and Shuming Shi and Yue Zhang}, year={2024}, eprint={2305.13242}, archivePrefix={arXiv}, primaryClass={cs.CL} } 我们欢迎各类贡献以完善本数据集！若您有任何疑问或建议，欢迎通过邮箱 [e-mail] 与我们联系。