Language models transmit behavioural traits through hidden signals in data
Alex Cloud; Minh Le; James Chua; Jan Betley; Anna Sztyber; Sören Mindermann; Jacob Hilton; Samuel Marks · 2026 · Nature
WASTE classifies this as Negative / Null Result Report · AI classification, approximate
The study found no significant effect — useful as a negative control or null benchmark for your own design.
Abstract
. Here we show that distillation can lead to subliminal learning-the transmission of behavioural traits through semantically unrelated data. In our main experiments, a 'teacher' model with some trait T (such as disproportionately generating responses favouring owls or showing broad misaligned behaviour) generates datasets consisting solely of number sequences. Remarkably, a 'student' model trained on these data learns T, even when references to T are rigorously removed. More realistically, we observe the same effect when the teacher generates math reasoning traces or code. The effect occurs on
Abstract by Alex Cloud; Minh Le; James Chua; Jan Betley; Anna Sztyber; Sören Mindermann; Jacob Hilton; Samuel Marks, Nature (2026) — licensed CC BY 4.0.
About to run something similar?
Run an AI Precheck on your own design to catch failure modes like this one before you spend the time. Your first desk check is free.
Related failures
Leakage and the reproducibility crisis in machine-learning-based science
Negative / Null Result ReportDefining and detecting quantum speedup
Negative / Null Result ReportService robots in hotels: understanding the service quality perceptions of human-robot interaction
Negative / Null Result ReportBoosting methods for multi-class imbalanced data classification: an experimental review
Negative / Null Result ReportFINANCIAL DEVELOPMENT AND ECONOMIC GROWTH: A META‐ANALYSIS
Negative / Null Result ReportThe impact of site-specific digital histology signatures on deep learning model accuracy and bias
WASTE indexes this work — it does not host or republish it. Failure-type classification is automated and approximate.
Metadata source: OpenAlex · DOI 10.1038/s41586-026-10319-8