Embeddings reliably capture authorial stylistic features in French literary texts, and these signals persist after LLM rewriting while showing model-specific patterns.
arXiv preprint arXiv:2505.00679 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
The paper argues, without completed experiments, that zero-width Unicode steganography could be layered on top of imitation, translation, and obfuscation to evade stylometric authorship attribution.
citing papers explorer
-
Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
Embeddings reliably capture authorial stylistic features in French literary texts, and these signals persist after LLM rewriting while showing model-specific patterns.
-
Unveiling Unicode's Unseen Underpinnings in Undermining Authorship Attribution
The paper argues, without completed experiments, that zero-width Unicode steganography could be layered on top of imitation, translation, and obfuscation to evade stylometric authorship attribution.