chatgpt-comparison-detection issues

无法复现论文中的结果 Unable to reproduce the results in the paper

我尝试复现中论文中的结果，现在我是直接导入hugging face上的chatgpt-detector-roberta作为model和tokenizer，根据页面上的描述这是由mixed数据集训练的，在论文中对raw-full的F1 score应该为99.44，但我没办法得到这个数据，我使用的数据集是在hc3中readme中的谷歌网盘下载的，以下是我得到的结果 {'0': {'precision': 0.9994103425909546, 'recall': 0.9951852504256943, 'f1-score': 0.9972933215651661, 'support': 17031.0}, '1': {'precision': 0.9898640296662546, 'recall': 0.9987528061860813, 'f1-score': 0.994288552272163, 'support': 8018.0}, 'accuracy': 0.9963271986905665, 'macro avg': {'precision': 0.9946371861286046, 'recall': 0.9969690283058878, 'f1-score':...

ohgodaaaa

404 on downloading the training and testing corpus

1

![image](https://github.com/Hello-SimpleAI/chatgpt-comparison-detection/assets/48833215/98a9c00c-71a6-46f5-a1ac-85a7b740fab2) Could you please re-upload the link?

LebronXierunfeng

What is the license?

4

hi, may I know what is the license of the released dataset? We may use it for commercial production so need to know what the license is exactly. Thanks!

jind11

模型代码

您好，想问一下您检测的模型代码（论文中的第二个模型基于robert）是在哪呢

mq55

Where can I find the checkpoints of GLTR model? or can you propose what are the training subset (number of human and chatgpt genrated sentence) used for training GLTR and roberta models?)

3

YashVadi

Do we have data splits?

2

Hi dear developers, I am wondering whether data splits (e.g. train/val/test) has been released; I saw a issue 3 weeks ago with an official reply saying "We will release the...

sairights