Unsupervised style representations learned via paraphrase inversion enable competitive few-shot and zero-shot AI-text detection with better generalization to unseen LLMs than supervised baselines.
Catch Me If You Can? Not Yet: LLM s Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A decoder is trained on 1010 style features to map style representations back to prompts, outperforming direct LLM prompting on style recovery, imitation, and steering tasks.
Embeddings reliably capture authorial stylistic features in French literary texts, and these signals persist after LLM rewriting while showing model-specific patterns.
citing papers explorer
-
Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion
Unsupervised style representations learned via paraphrase inversion enable competitive few-shot and zero-shot AI-text detection with better generalization to unseen LLMs than supervised baselines.
-
Interpreting Style Representations via Style-Eliciting Prompts
A decoder is trained on 1010 style features to map style representations back to prompts, outperforming direct LLM prompting on style recovery, imitation, and steering tasks.
-
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.