2025/11/06 by Matthew Bozoukov, Bozoukov, Matthew, Matthew Nguyen +7 · 1 voice
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Behavioral analysis #Behavioral economics #Behavioral modeling #Behavioral pattern #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Feature (linguistics) #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #cs.AI #cs.CL #cs.LG
paper · pdf · open access · doi:10.48550/arxiv.2511.04875
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/11/06 · arxiv published 2025/11/06 · arxiv updated 2025/11/10 · openalex created_date 2025/11/11 · openalex updated_date 2026/07/28
Recent studies have revealed that LLMs can exhibit behavioral self-awareness: the ability to accurately describe or predict their own learned behaviors without explicit supervision. This capability raises safety concerns as it may, for example, allow models to better conceal their true abilities during evaluation. We attempt to characterize the minimal conditions under which such self-awareness emerges, and the mechanistic processes through which it manifests. Through controlled finetuning experiments on instruction-tuned LLMs with low-rank adapters (LoRA), we find: (1) that self-awareness can be reliably induced using a single rank-1 LoRA adapter; (2) that the learned self-aware behavior can be largely captured by a single steering vector in activation space, recovering nearly all of the fine-tune's behavioral effect; and (3) that self-awareness is non-universal and domain-localized, with independent representations across tasks. Together, these findings suggest that behavioral self-awareness emerges as a domain-specific, linear feature that can be easily induced and modulated.