arxiv
PublishedApril 24, 2026 at 4:00 AM
—neutral
Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI
Publisher summary· verbatim
arXiv:2604.21300v1 Announce Type: new Abstract: Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations between authors
Discussion
No replies yet. Be first.
Originally published on arxiv ↗