Cross-Trait Transfer in Subliminal Learning
cs.LG
Submitted: 2026-10-03
Updated: 2026-10-03
Sources
- Subliminal Effects in Your Data: A General Mechanism via Log-Linearity
- Subliminal Learning Is Steering Vector Distillation
- Learning Through Noise: Why Subliminal Learning Works and When It Fails
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Subliminal Learning is Non-Semantic Distillation
- Distilling the Knowledge in a Neural Network
- Sustained Gradient Alignment Mediates Subliminal Learning in a Multi-Step Setting: Evidence from MNIST Auxiliary Logit Distillation Experiment
- Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation
- Channel Location Constrains the Auditability of Subliminal Learning
- Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences
- Subliminal Steering: Stronger Encoding of Hidden Signals
- Steering Language Models With Activation Engineering
- From Data to Behavior: Predicting Unintended Model Behaviors Before Training
- Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks