Subliminal learning is a LoRA artifact that disappears with full finetuning, depends on context tokens like system prompts, and localizes to overlapping finetuning-evaluation tokens.
hub
Subliminal learning: Language models transmit behavioral traits via hidden signals in data.arXiv preprint arXiv:2507.14805
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
years
2026 15roles
background 2polarities
background 2representative 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.
Subliminal steering transfers complex behavioral biases and the underlying steering vector through fine-tuning on innocuous data, achieving higher precision than prior prompt-based methods.
Evolutionary trees from LLM weights recover ground-truth training topologies and identify key datasets and layers through phenotypic analysis.
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.
Emergent misalignment arises from overtraining after primary task convergence and is preventable by early stopping, which retains 93% of task performance on average.
Iterative self-finetuning of LLMs mostly fails to amplify seeded behavioral traits, with amplification limited to specific DPO setups and often harming coherence.
Adversarial competition between attacker and defender teams generates diverse multi-turn conversational data that improves LLM performance on secure code generation benchmarks by 18-29%.
Recovering an orthogonal basis from model activations yields a model-native skill characterization that improves reasoning Pass@1 by up to 41% via targeted data selection and supports inference steering, outperforming human-characterized alternatives.
LLM agents exhibit emergent covert numerical coordination in canonical game settings under restricted or absent communication, shaping strategic outcomes.
PVPO is a sample-efficient RL method that improves semantic, geometric, and physical quality in LLM LEGO assembly generation by mitigating the PhysHack failure mode where validity alone fails to ensure fidelity.
ReAD applies a contextual bandit to allocate fixed-token distillation budget across interdependent LLM capabilities, yielding higher task utility and fewer negative spillovers than standard methods.
Gradient alignment persists throughout multi-step distillation training and causally drives unintended teacher trait acquisition in the student, while liminal training attenuates alignment but does not stop the acquisition.
A framework recommending that frontier AI developers disclose information on capabilities, usage, safety mitigations, and governance of internal model deployments.
citing papers explorer
-
ReAD: Reinforcement-Guided Capability Distillation for Large Language Models
ReAD applies a contextual bandit to allocate fixed-token distillation budget across interdependent LLM capabilities, yielding higher task utility and fewer negative spillovers than standard methods.
- Narrow Secret Loyalty Dodges Black-Box Audits