jagoldz/gahd

Model Card

Model Description

We fine-tuned this gelectra-large model for four rounds of dynamic adversarial data collection to create the GAHD dataset. In each round annotators created examples by trying to trick the model into a misclassification. We explored different ways of supporting annotators in finding model-tricking examples during the data collection. This is the final model (R4) in our paper. The model classifies text into "hate speech" (1) or "not-hate speech" (0).

Please check out our paper for further details about the training procedure (Appendix C) or evaluation (Section 4).

• paper: https://arxiv.org/abs/2403.19559
• GAHD dataset on Huggingface: https://huggingface.co/datasets/jagoldz/gahd
• GAHD dataset on GitHub: https://github.com/jagol/gahd

Citation

When using this model or the GAHD dataset, please cite our preprint on Arxiv:

@misc{goldzycher2024improving,
      title={Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset}, 
      author={Janis Goldzycher and Paul Röttger and Gerold Schneider},
      year={2024},
      eprint={2403.19559},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}