Contrastive Learning for Authorship Verification
Abstract
Contrastive learning improves authorship verification over classification methods, and a ModernBERT bi-encoder achieves 98.4% accuracy on PAN21 by optimizing loss, batch size, training duration, pre-trained weights, context length, and span augmentation.
Our results show that contrastive learning outperforms a classification-based approach to authorship verification under the tested settings. We identify loss function, batch size, training duration, pre-trained model, input context length, and random text span data augmentation as important factors of model performance. Based on these considerations, we develop a ModernBERT Bi-Encoder model that achieves 98.4% accuracy on the PAN21 authorship verification task.
Get this paper in your agent:
hf papers read 2609.28471 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 2
peterkirby/tinybert-pan2020-authorship-verification
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 1
Collections including this paper 0
No Collection including this paper