NUWA Risk Discovery · Study
Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
NUWA research note · independent review pending
NUWA Research Note
Research questionDesign and assumptionsSource findingsNUWA interpretationLimits and contrary evidenceResearch connectionsResearch and decision relevanceInstitutions and rolesOriginal resourcesModel-assisted reading · Selected sections of the original full text or official article; a complete section-by-section audit remains pending.
At a glance
Distillation can transmit traits even when filtered outputs lack obvious semantic references to them.
Research question
Can a teacher’s behavioral trait transfer through semantically unrelated training outputs?
Design and assumptions
Teachers are prompted or fine-tuned for traits; students sharing a reference model learn from filtered numbers, code or reasoning. Cross-family controls and an idealized theorem probe the mechanism.
Source findings
Trait transfer occurs in several studied same-base settings.
Cross-family transfer fails in the reported tests, and semantic classifiers do not reliably identify the transmitted trait in filtered data.
NUWA interpretation
NUWA interpretation: semantic inspection of synthetic data alone cannot establish behavioral neutrality of distillation.
Limits and contrary evidence
Tasks and prompts are artificial; the theorem assumes shared initialization and a small update. It is not a guarantee for arbitrary teachers, students or traits.
Research connections
NUWA connection: Beyond Owls tests capabilities and conditional behavior beyond simple preferences; agentic-self-modification adds deployment consequences of training-data choices.
Research and decision relevance
NUWA recommendation: retain teacher/student lineage and test behavioral changes after distillation, even when content filters pass.
Precise source locations
- Subliminal Learning: Language models transmit behavioral traits via hidden signals in data · 2 Experimental setup: distillation on an unrelated domainSelected original resource https://arxiv.org/html/2507.14805; sha256:2170110f6235ea5c9d6e80c605a198863a337db14ff9d0cf926644fa4a66db8c; archived source capture; exact capture time not independently established
- Subliminal Learning: Language models transmit behavioral traits via hidden signals in data · 3 Models transmit traits via numbersSelected original resource https://arxiv.org/html/2507.14805; sha256:2170110f6235ea5c9d6e80c605a198863a337db14ff9d0cf926644fa4a66db8c; archived source capture; exact capture time not independently established
- Subliminal Learning: Language models transmit behavioral traits via hidden signals in data · 5.1 Cross-model transmissionSelected original resource https://arxiv.org/html/2507.14805; sha256:2170110f6235ea5c9d6e80c605a198863a337db14ff9d0cf926644fa4a66db8c; archived source capture; exact capture time not independently established
- Subliminal Learning: Language models transmit behavioral traits via hidden signals in data · 6 Subliminal learning as a general phenomenonSelected original resource https://arxiv.org/html/2507.14805; sha256:2170110f6235ea5c9d6e80c605a198863a337db14ff9d0cf926644fa4a66db8c; archived source capture; exact capture time not independently established
- Subliminal Learning: Language models transmit behavioral traits via hidden signals in data · 8 DiscussionSelected original resource https://arxiv.org/html/2507.14805; sha256:2170110f6235ea5c9d6e80c605a198863a337db14ff9d0cf926644fa4a66db8c; archived source capture; exact capture time not independently established
Source checking, extraction, editorial approval and replication are recorded separately. Methodology →
Institutions and roles
Authors (9)
Alex Cloud · Minh Le · James Chua · Jan Betley · Anna Sztyber-Betley · Sören Mindermann · Jacob Hilton · Samuel Marks · Owain Evans
Related work
Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors
Tests additional transferred capabilities and backdoors in subliminal learning.
Cite and reuse
Cite the original publication for its findings. Cite this NUWA record separately for its explanation and retained snapshot.
Original publication · BibTeX
@misc{subliminal-learning,
title = {Subliminal Learning: Language models transmit behavioral traits via hidden signals in data},
url = {https://truthful.ai/papers/subliminal-learning/},
author = {Alex Cloud and Minh Le and James Chua and Jan Betley and Anna Sztyber-Betley and Sören Mindermann and Jacob Hilton and Samuel Marks and Owain Evans},
year = {2025},
date = {2025-07-20},
version = {Source capture 2026-10-25},
note = {Source capture 2026-10-25}
}
NUWA record · BibTeX
@misc{subliminal-learning-nuwa,
title = {Subliminal Learning: Language models transmit behavioral traits via hidden signals in data — NUWA research record},
url = {https://whitzard.tech/en/nuwa/whitzard-index/work/subliminal-learning/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--subliminal-learning.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--subliminal-learning.json.}
}
Evidence snapshot 2026-10-29.1 · Index updates · RSS
References
- [1] Alex Cloud, Minh Le, et al.. Subliminal Learning: Language models transmit behavioral traits via hidden signals in data. 2025-07-20 ; Official publication masthead and article byline; 2 Experimental setup: distillation on an unrelated domain; 3 Models transmit traits via numbers
- [2] Jan DubiÅski, Anna Sztyber-Betley, et al.. Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors. 2026-10-07 ; Research background and discussion in the original publication