Contrastive Learning for Authorship Verification

Abstract: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.

Published in the proceedings of CLEF 2026. Code: this https URL

Computation and Language (cs.CL); Machine Learning (cs.LG)

arXiv:2609.28471 [cs.CL]

(or arXiv:2609.28471v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.28471 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

Experimental IR Meets Multilinguality, Multimodality, and Interaction (CLEF 2026), LNCS 17087, pp. 92-102, Springer (2027)

https://doi.org/10.1007/978-3-032-39150-6_7 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.