作者位次 #3/5ACL 2026Poster· Natural Language Processing
Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI
Hieu Man · Van-Cuong Pham · Nghia Trung Ngo · Franck Dernoncourt · Thien Huu Nguyen
摘要
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’ writing styles and topics, leading to poor...