Steering LLM residual streams with random sparse vectors creates detectable self-recognition fingerprints that enable over 98% accurate attribution of generated text to specific models without degrading output quality.
arXiv preprint arXiv:2508.13152 , url=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
An image-semantic guided method enhances MLLMs for detecting AI-generated modern Chinese poetry by combining poem text with visual representations of content, achieving 85.65% Macro-F1 with Gemini and outperforming text baselines and RoBERTa.
A multi-level framework that models local and global relations among token detection scores to improve machine-generated text detection with low overhead.
citing papers explorer
-
LLM Self-Recognition: Steering and Retrieving Activation Signatures
Steering LLM residual streams with random sparse vectors creates detectable self-recognition fingerprints that enable over 98% accurate attribution of generated text to specific models without degrading output quality.
-
Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs
An image-semantic guided method enhances MLLMs for detecting AI-generated modern Chinese poetry by combining poem text with visual representations of content, achieving 85.65% Macro-F1 with Gemini and outperforming text baselines and RoBERTa.
-
Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection
A multi-level framework that models local and global relations among token detection scores to improve machine-generated text detection with low overhead.