SOURCE-LINKED INTELLIGENCE

Contrastive Learning for Authorship Verification

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

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.

Read original source ↗ Open in workspace

recordType

paper

region

Global