antortl commited on
Commit
601c141
1 Parent(s): 4441554

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -35
README.md CHANGED
@@ -1,41 +1,7 @@
1
- ---
2
- datasets:
3
- - Hello-SimpleAI/HC3
4
- language:
5
- - en
6
- pipeline_tag: text-classification
7
- tags:
8
- - chatgpt
9
- ---
10
 
11
- # Model Card for `Hello-SimpleAI/chatgpt-detector-roberta`
12
 
13
- This model is trained on **the mix of full-text and splitted sentences** of `answer`s from [Hello-SimpleAI/HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3).
14
 
15
- More details refer to [arxiv: 2301.07597](https://arxiv.org/abs/2301.07597) and Gtihub project [Hello-SimpleAI/chatgpt-comparison-detection](https://github.com/Hello-SimpleAI/chatgpt-comparison-detection).
16
 
17
 
18
- The base checkpoint is [roberta-base](https://huggingface.co/roberta-base).
19
- We train it with all [Hello-SimpleAI/HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3) data (without held-out) for 1 epoch.
20
 
21
- (1-epoch is consistent with the experiments in [our paper](https://arxiv.org/abs/2301.07597).)
22
-
23
- ## Citation
24
-
25
- Checkout this papaer [arxiv: 2301.07597](https://arxiv.org/abs/2301.07597)
26
-
27
- ```
28
- @article{guo-etal-2023-hc3,
29
- title = "How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection",
30
- author = "Guo, Biyang and
31
- Zhang, Xin and
32
- Wang, Ziyuan and
33
- Jiang, Minqi and
34
- Nie, Jinran and
35
- Ding, Yuxuan and
36
- Yue, Jianwei and
37
- Wu, Yupeng",
38
- journal={arXiv preprint arxiv:2301.07597}
39
- year = "2023",
40
- }
41
- ```
 
 
 
 
 
 
 
 
 
 
1
 
 
2
 
3
+ # Model Card for `Ludwigsrls/roby`
4
 
 
5
 
6
 
 
 
7