Subliminal learning is steering vector distillation: a student fine-tuned on a steered teacher's outputs learns to imitate the steering vector.
Thought virus: Viral misalignment via subliminal prompting in multi-agent systems.arXiv preprint arXiv:2603.00131
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Steering language models with intermittent implicit trait reinforcements reduces misalignment contagion in multi-agent social dilemma games more effectively than system prompt repetition.
Emergent and subliminal misalignment in LLMs arise from data structure interactions and transfer via benign distillation data, with stronger effects under shared functional structure and on-policy settings.
Introduces ANIS as an endogenous, six-layer immune architecture for AI agents with taxonomy of viruses/vaccines and a meta-cognitive Harness Triad for continual adaptation.
citing papers explorer
-
Subliminal Learning Is Steering Vector Distillation
Subliminal learning is steering vector distillation: a student fine-tuned on a steered teacher's outputs learns to imitate the steering vector.
-
Mitigating Misalignment Contagion by Steering with Implicit Traits
Steering language models with intermittent implicit trait reinforcements reduces misalignment contagion in multi-agent social dilemma games more effectively than system prompt repetition.
-
Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
Emergent and subliminal misalignment in LLMs arise from data structure interactions and transfer via benign distillation data, with stronger effects under shared functional structure and on-policy settings.
-
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
Introduces ANIS as an endogenous, six-layer immune architecture for AI agents with taxonomy of viruses/vaccines and a meta-cognitive Harness Triad for continual adaptation.