# Towards Identifying the Dataset Biases Causing Phantom Transfer

arXiv: https://arxiv.org/abs/2609.14449 · HTML: https://mlsanity.com/paper/2609.14449/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [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)
- [Subliminal Effects in Your Data: A General Mechanism via Log-Linearity](https://mlsanity.com/paper/2602.04863/) (2026)
- [Subliminal Learning Is Steering Vector Distillation](https://mlsanity.com/paper/2606.00995/) (2026)
- [From Data to Behavior: Predicting Unintended Model Behaviors Before Training](https://mlsanity.com/paper/2602.04735/) (2026)
- [You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases](https://mlsanity.com/paper/2603.09517/) (2026)
- [Sustained Gradient Alignment Mediates Subliminal Learning in a Multi-Step Setting: Evidence from MNIST Auxiliary Logit Distillation Experiment](https://mlsanity.com/paper/2604.25779/) (2026)
- [Learning Through Noise: Why Subliminal Learning Works and When It Fails](https://mlsanity.com/paper/2605.23645/) (2026)
- [Channel Location Constrains the Auditability of Subliminal Learning](https://mlsanity.com/paper/2606.22019/) (2026)
- [Subliminal Learning is a LoRA Artifact](https://mlsanity.com/paper/2606.00831/) (2026)
- [Covert Influence Between Language Models](https://mlsanity.com/paper/2606.04071/) (2026)
- [Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF](https://mlsanity.com/paper/2607.10750/) (2026)

## Abstract (arXiv)

Recent work has shown that a teacher model can transfer a bias to a student through a dataset from which every explicit reference to that bias has been filtered out, and that none of the tested data-level defenses reliably removes or detects such a bias, even when the defender knows what to look for. To shed light on the hidden traces these biases leave, we embed a dataset's completions with Sentence-BERT, subtract the embeddings of clean reference completions, and compare the result to an open vocabulary of candidate topics. This simple signature identifies the topic of the bias with a Matthews correlation coefficient of 0.83 when the attacker's teacher model is known, and 0.46 when it is not. We also observe that different teacher models appear to express the same bias through different vocabulary.