Human written vs. AI written news classifier

Trained on the Hungarian news data from: https://huggingface.co/datasets/tum-nlp/neural_news

Base model:

https://huggingface.co/FacebookAI/xlm-roberta-base

Data

See below for data splits: Data Splits

Results

See below for accuracy metrics: Metrics

Paper

@article{uyuk2024crafting,
  title={Crafting Tomorrow's Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian},
  author={{\"U}y{\"u}k, Cem and Rov{\'o}, Danica and Kolli, Shaghayegh and Varol, Rabia and Groh, Georg and Dementieva, Daryna},
  journal={arXiv preprint arXiv:2408.10724},
  year={2024}
}
Downloads last month
10
Safetensors
Model size
125M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train tum-nlp/neural-news-discriminator-RoBERTa-hu

Collection including tum-nlp/neural-news-discriminator-RoBERTa-hu