SOURCE-LINKED INTELLIGENCE

Can Data Attribution Filter Out Subliminal Learning? Not Reliably

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

Subliminal learning allows language models to transmit behavioral traits through training data with no obvious semantic relationship to those traits, undermining content-based data filtering as a safety intervention. Training data attribution offers an alternative: it identifies the training examples responsible for a given model behavior, independent of their semantic content, and so may apply in exactly the cases where semantic inspection fails. We evaluate three gradient-based attribution methods (GradCos, a contrastive GradCos variant, and EK-FAC) across three models, comparing them agains

Read original source ↗ Open in workspace

recordType: paper
region: Global

Evidence & attribution

arXiv · AI, language, vision and robotics · 2026-09-17T10:34:18.000Z
arXiv · Artificial Intelligence · 2026-09-17T10:34:18.000Z

First collected: 2026-09-19T20:26:32.566Z. This is not the publication date.