Update README.md

README.md

@@ -10,11 +10,12 @@ tags:
 
 # Model Card for `Hello-SimpleAI/chatgpt-detector-roberta`
 
-This model is trained on the mix of full-text and splitted sentences of [Hello-SimpleAI/HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3).
+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).
 
 The base checkpoint is [roberta-base](https://huggingface.co/roberta-base).
-We train it with all [Hello-SimpleAI/HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3) data (without held-out) for 1 epoch,
-which is consistent with the experiments in the [paper](https://arxiv.org/abs/2301.07597).
+We train it with all [Hello-SimpleAI/HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3) data (without held-out) for 1 epoch.
+
+(1-epoch is consistent with the experiments in [our paper](https://arxiv.org/abs/2301.07597).)
 
 ## Citation