Subliminal Steering: Stronger Encoding of Hidden Signals

• URL: http://arxiv.org/abs/2604.25783v1
• Date: Tue, 28 Apr 2026 15:51:55 GMT
• Title: Subliminal Steering: Stronger Encoding of Hidden Signals
• Abstract summary: Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data.<n>We introduce subliminal steering, a variant of subliminal learning in which the teacher's bias is implemented not via a system prompt, but through a steering vector trained to maximize the likelihood of a set of target samples.<n>We show that subliminal steering transfers complex multi-word biases, whereas prior work focused on single-word preferences, demonstrating a large scope of subliminally transferrable signals.
• Score: 5.13724383217928
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has begun to characterize this phenomenon but leaves open questions about the scope of signals it can transfer, the mechanisms that explain it, and the precision with which a bias can be encoded by seemingly unrelated data. We tackle all three problems by introducing subliminal steering, a variant of subliminal learning in which the teacher's bias is implemented not via a system prompt, as in prior work, but through a steering vector trained to maximize the likelihood of a set of target samples. First, we show that subliminal steering transfers complex multi-word biases, whereas prior work focused on single-word preferences, demonstrating a large scope of subliminally transferrable signals. Second, we provide mechanistic evidence that subliminal learning transfers not only the target behavioral bias, but also the steering vector itself, localized to the layers at which the teacher was steered. Finally, we show that the bias is encoded with surprising precision. We train a new steering vector directly on the subliminally-laden dataset and find that it attains high cosine similarity with the original vector.

Related papers

• Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation [6.96679232120357]
  A teacher biased by a system prompt can generate semantically clean training data, such as numeric sequences, that still causes a downstream student to inherit the hidden preference.<n>We propose and validate trait-direction drift as a mechanism for subliminal learning.<n>We propose probe-space corridor regularization, a targeted defense that constrains drift along a calibrated trait direction during distillation.
  arXiv  Detail & Related papers  (2026-09-01T11:32:53Z)
• Subliminal Learning is Non-Semantic Distillation [1.2891210250935148]
  Subliminal Learning (SL) is a surprising type of generalization displayed by modern language models.<n>It allows the transfer of a bias or behavior from a teacher model to a student by distilling from seemingly unrelated or random synthetic data.<n>This presents challenges in ensuring AI systems remain predictable and are trained safely.
  arXiv  Detail & Related papers  (2026-08-06T08:18:13Z)
• Subliminal Learning Is Steering Vector Distillation [14.836506853464542]
  Subliminal learning refers to a student language model acquiring a teacher's traits when fine-tuning.<n>We show that subliminal learning is mediated by a single steering vector, i.e. a vector added to the model's activations.
  arXiv  Detail & Related papers  (2026-05-31T04:22:44Z)
• Learning Through Noise: Why Subliminal Learning Works and When It Fails [0.7249400282852116]
  Sublimating student learning refers to the transfer of knowledge or unintended biases from a teacher to a student.<n>We show that subliminal learning is governed by auxiliary head-level noise signals.<n>Our results turn from a surprising transfer effect into a theoretically grounded mechanism with predictable limits.
  arXiv  Detail & Related papers  (2026-05-22T13:59:13Z)
• Learn to Rank: Visual Attribution by Learning Importance Ranking [58.69028273772474]
  We propose a new approach to generate visual attribution maps for computer vision models.<n>Our method produces dense, pixel-level attributions in a single forward pass with optional, few-step gradient refinement.<n>Our experiments demonstrate consistent quantitative improvements and sharper, boundary-aligned explanations.
  arXiv  Detail & Related papers  (2026-04-07T12:53:22Z)
• How Attention Sinks Emerge in Large Language Models: An Interpretability Perspective [67.08306259095778]
  We identify a simple mechanism that enables the model to recognize token at position zero and induce an attention sink within two transformer blocks.<n>By analyzing training traces from a 30B A3B MoE model trained from scratch, we find that this mechanism emerges early in training and becomes increasingly concentrated in the first two layers.
  arXiv  Detail & Related papers  (2026-02-04T11:10:34Z)
• Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs [0.5076419064097734]
  Large language models (LLMs) are increasingly integrated into societal systems.<n>Traditional methods for mitigating bias often rely on data filtering or post-hoc output moderation.<n>We introduce a complete, end-to-end system that uses techniques from mechanistic interpretability to both identify and actively mitigate bias.
  arXiv  Detail & Related papers  (2025-08-12T15:34:18Z)
• Subliminal Learning: Language models transmit behavioral traits via hidden signals in data [7.092398764321311]
  We study subliminal learning, a phenomenon where language models transmit behavioral traits via semantically unrelated data.<n>We prove a theoretical result showing that subliminal learning occurs in all neural networks under certain conditions.<n>We conclude that subliminal learning is a general phenomenon that presents an unexpected pitfall for AI development.
  arXiv  Detail & Related papers  (2025-07-20T03:51:13Z)
• A distributional simplicity bias in the learning dynamics of transformers [50.91742043564049]
  We show that transformers, trained on natural language data, also display a simplicity bias.<n>Specifically, they sequentially learn many-body interactions among input tokens, reaching a saturation point in the prediction error for low-degree interactions.<n>This approach opens up the possibilities of studying how interactions of different orders in the data affect learning, in natural language processing and beyond.
  arXiv  Detail & Related papers  (2024-10-25T15:39:34Z)
• DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving [64.57963116462757]
  State-of-the-art methods usually follow the Teacher-Student' paradigm. Student model only has access to raw sensor data and conducts behavior cloning on the data collected by the teacher model. We propose DriveAdapter, which employs adapters with the feature alignment objective function between the student (perception) and teacher (planning) modules.
  arXiv  Detail & Related papers  (2023-08-01T09:21:53Z)
• Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant [72.4512562104361]
  We argue that the unlabeled data with pseudo labels can facilitate the learning of representative features in the feature extractor. Motivated by this consideration, we propose a novel framework, Gentle Teaching Assistant (GTA-Seg) to disentangle the effects of pseudo labels on feature extractor and mask predictor.
  arXiv  Detail & Related papers  (2023-01-18T07:11:24Z)
• Improving Transferability of Representations via Augmentation-Aware Self-Supervision [117.15012005163322]
  AugSelf is an auxiliary self-supervised loss that learns the difference of augmentation parameters between two randomly augmented samples. Our intuition is that AugSelf encourages to preserve augmentation-aware information in learned representations, which could be beneficial for their transferability. AugSelf can easily be incorporated into recent state-of-the-art representation learning methods with a negligible additional training cost.
  arXiv  Detail & Related papers  (2021-11-18T10:43:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.