Commit
•
30b3060
1
Parent(s):
52f6289
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,4 +21,43 @@ tags:
|
|
| 21 |
- ai-detection
|
| 22 |
---
|
| 23 |
|
| 24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
- ai-detection
|
| 22 |
---
|
| 23 |
|
| 24 |
+
# Machine-generated text (MGT)-detection by fine-tuning of language models
|
| 25 |
+
|
| 26 |
+
This is a text classification model for detecting machine-generated text and is fine-tuned from **RoBERTa-base** (see https://huggingface.co/roberta-base). The model is trained on generated scientific abstracts by **ChatGPT** and real scientific abstracts of arxiv papers.
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
## Fine-tuned models
|
| 32 |
+
|
| 33 |
+
| Base-model | RoBERTa-base | Bloomz-560m | Bloomz-1b7 | Bloomz-3b |
|
| 34 |
+
|------------|--------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------|
|
| 35 |
+
| Wiki | [roberta-wiki](https://huggingface.co/andreas122001/roberta-academic-detector) | [Bloomz-560m-wiki](https://huggingface.co/andreas122001/bloomz-560m-wiki-detector) | [Bloomz-1b7-wiki](https://huggingface.co/andreas122001/bloomz-1b7-wiki-detector) | [Bloomz-3b-wiki](https://huggingface.co/andreas122001/bloomz-3b-wiki-detector) |
|
| 36 |
+
| Academic | [roberta-academic](https://huggingface.co/andreas122001/roberta-wiki-detector) | [Bloomz-560m-academic](https://huggingface.co/andreas122001/bloomz-560m-academic-detector) | [Bloomz-1b7-academic](https://huggingface.co/andreas122001/bloomz-1b7-academic-detector) | [Bloomz-3b-academic](https://huggingface.co/andreas122001/bloomz-3b-academic-detector) |
|
| 37 |
+
| Mixed | [roberta-mixed](https://huggingface.co/andreas122001/roberta-mixed-detector) | [Bloomz-560m-mixed](https://huggingface.co/andreas122001/bloomz-560m-mixed-detector) | [Bloomz-1b7-mixed](https://huggingface.co/andreas122001/bloomz-1b7-mixed-detector) | [Bloomz-3b-mixed](https://huggingface.co/andreas122001/bloomz-3b-mixed-detector) |
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
## Credits
|
| 41 |
+
|
| 42 |
+
- [GPT-wiki-intro](https://huggingface.co/datasets/aadityaubhat/GPT-wiki-intro), by Aaditya Bhat
|
| 43 |
+
- [arxiv-abstracts-2021](https://huggingface.co/datasets/gfissore/arxiv-abstracts-2021), by Giancarlo
|
| 44 |
+
- [Bloomz](bigscience/bloomz), by BigScience
|
| 45 |
+
- [RoBERTa](https://huggingface.co/roberta-base), by Liu et. al.
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
## Citation
|
| 51 |
+
|
| 52 |
+
Please use the following citation:
|
| 53 |
+
|
| 54 |
+
```
|
| 55 |
+
@misc {sivesind_2023,
|
| 56 |
+
author = { {Nicolai Thorer Sivesind} and {Andreas Bentzen Winje}},
|
| 57 |
+
title = { MGT-Detection },
|
| 58 |
+
url = {https://huggingface.co/andreas122001/roberta-academic-detector}
|
| 59 |
+
year = 2023,
|
| 60 |
+
publisher = { Hugging Face }
|
| 61 |
+
}
|
| 62 |
+
```
|
| 63 |
+
|