arxiv.orgpaperContrastive Learning for Authorship Verification
This arXiv paper studies authorship verification (determining if two texts share an author) and shows contrastive learning beats a classification-based baseline. The authors ablate loss function, batch size, training duration, pretrained backbone, input context length, and random text span augmentation, then build a ModernBERT bi-encoder that reaches 98.4% accuracy on the PAN21 authorship verification benchmark.
TL;DR Contrastive ModernBERT bi-encoder hits 98.4% accuracy on PAN21 authorship verification, beating classification-based baselines.
Organisations named here
- PAN21
Technologies named here
- ModernBERT Bi-Encoder
- ModernBERT
Techniques named here
- Contrastive learning
- Classification-based approach
- Random text span data augmentation
Related in research