Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation
A student model trained on pure uniform noise can still inherit its teacher's digit-classification ability, provided the two share initialization. Previous work proves this transfer is guaranteed when the teacher's learning rate is small enough, but does not explain where in the network the channel lives or what sets its capacity. Working in an MLP distillation setting on MNIST, we show these channels are not purely informational: geometric alignment gates access to the information the channel c
Record details
Published: 5 July 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Children & education
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
D2PO: Optimizing Diffusion Samplers via Dynamic Preference
arXiv · 7 July 2026
Fine-Tuning, Retrieval-Augmented Generation, and Hybrid Large Language Models for Postoperative Decision Support: Comparative Analysis
JMIR (Journal of Medical Internet Research) · 14 July 2026
LLM sentiment quantification reveals selective alignment with human course-evaluation raters
Computers and Education: Artificial Intelligence · 14 July 2026
A framework for evaluation of large language models in essay assessment: Reliability, alignment, and causal reasoning
Computers and Education: Artificial Intelligence · 14 July 2026
Phoneme-Level Mispronunciation Screening in Polish-Speaking Children with an Explainable Assistant
arXiv · 23 June 2026
ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation
arXiv · 22 June 2026
How to cite this record
ethics.ai (5 July 2026), “Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation,” evidence record 227, https://ethics.ai/record/227 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.