# You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases

arXiv: https://arxiv.org/abs/2603.09517 · HTML: https://mlsanity.com/paper/2603.09517/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 49 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 6 of 6)

- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [Subliminal Learning: Language models transmit behavioral traits via hidden signals in data](https://mlsanity.com/paper/2507.14805/) (2025)
- [Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer](https://mlsanity.com/paper/2509.23886/) (2025)
- [Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI](https://mlsanity.com/paper/2511.01689/) (2025)

## Built on by (most cited first, 8 of 8)

- [Subliminal Learning Is Steering Vector Distillation](https://mlsanity.com/paper/2606.00995/) (2026)
- [Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer](https://mlsanity.com/paper/2605.12798/) (2026)
- [Channel Location Constrains the Auditability of Subliminal Learning](https://mlsanity.com/paper/2606.22019/) (2026)
- [Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence](https://mlsanity.com/paper/2608.12036/) (2026)
- [Towards Identifying the Dataset Biases Causing Phantom Transfer](https://mlsanity.com/paper/2609.14449/) (2026)
- [Can Data Attribution Filter Out Subliminal Learning? Not Reliably](https://mlsanity.com/paper/2609.20027/) (2026)
- [Post-Training Leaves Behavioral Shadows on Unrelated Decisions](https://mlsanity.com/paper/2609.29233/) (2026)
- [Imprinting: Knowledge Distillation Can Shift Student Behavior](https://mlsanity.com/paper/2610.18517/) (2026)

## Abstract (arXiv)

When language models are trained on synthetic data, they (student model) can covertly acquire behavioral traits from the data-generating model (teacher model). Subliminal learning refers to the transmission of traits from a teacher to a student model via training on data unrelated to those traits. Prior work demonstrated this in the training domains of number sequences, code, and math Chain-of-Thought traces including transmission of misaligned behaviors. We investigate whether transmission occurs through natural language paraphrases with fixed semantic content, and whether content explicitly contradicting the teacher's preference can block it. We find that training on paraphrases from a teacher system-prompted to love a particular animal increases a student's preference for that animal by up to 19 percentage points. This occurs when paraphrased content is semantically unrelated to the animal, or even when it explicitly expresses dislike. The transmission succeeds despite aggressive filtering to ensure paraphrase fidelity. This raises concerns for pipelines where models generate their own training data: content-based inspection cannot detect such transmission, and even preference-contradicting content fails to prevent it.