AINeutralarXiv – CS AI · 9h ago6/10
🧠
LLM Self-Recognition: Steering and Retrieving Activation Signatures
Researchers demonstrate that large language models can reliably self-recognize their own outputs through implicit signals encoded in generated text, and this capability can be amplified through targeted steering of internal activation patterns. By injecting sparse random vectors into a model's residual stream during generation, they create detectable fingerprints enabling attribution to specific LLMs with over 98% accuracy while maintaining text quality. This approach offers a practical alternative to traditional AI-generated content detection by leveraging models' natural representation structures.