Subliminal Learning

We find that language models can transfer capabilities through task-unrelated text. Post-training typically improves language models using task-specific data. Prior work on subliminal learning shows that information about these updates can pass through unrelated generations, but has largely focused on traits or preferences using extensive teacher outputs. We introduce Active Taskless Distillation (ATD), which achieves capability transfer using only a single word from the teacher per prompt. ATD probes the behavioral shadow of post-training by selecting prompts where the teacher and student's shared public ancestor is nearly indifferent between two ordinary words. A student initialized from this ancestor learns solely from the resulting prompt-word pairs, without target-task examples, teacher logits, or teacher parameters. In the primary coding experiment with Qwen2.5-1.5B, 5,664nses yield a 5.34 pp gain on HumanEval+ over an exact nuisance-matched control thadisrupts prompt-resperiments showtransfer in scientific knowledge, commonsense reasoning, and reading comprehensins across additional model generations, sizes, and families. Functional analyses show that the learned sid composable, andthat its strength tracks the teacher's update strength.

Subliminal learning allows language models to transmit behavioral traits through training data with no obvious semantic relationship to those traits, undermining content-based data filtering as a safety intervention. Training data attribution offers an alternative: it identifies the training examples responsible for a given model behavior, independent of their semantic content, and so may apply in exactly the cases where semantic inspection fails. We evaluate three gradient-based attribution methods (GradCos, a contrastive GradCos variant, and EK-FAC) across three models, comparing them against divergence tokens, a strong baseline previously shown to localize subliminal learning (albeit one that requires access to counterfactual teacher models). Filtering at the token level, EK-FAC mitigates a significant part of the effect, the other methods provide little benefit, and all mostly fall short of divergence tokens. Filtering entire samples is less effective for every method, though EK-FAC often gives a stronger signal than divergence tokens in this setting. Success is inconsistent across methods and settings: variants that work well for some model-preference combinations fail for others, and we do not identify a consistent explanation for these differences. Our results suggest that gradient-based attribution can identify data responsible for subliminal learning in some settings, but that some approximations are more reliable than others.

Subliminal learning is a phenomenon in which a distillation dataset transmits traits from the teacher model that are not legibly encoded in the dataset itself. This introduces a new challenge for model development and creates new risks from data poisoning. In this work, we use text optimization to detect subliminal learning effects and describe them as legible prompts. Subliminal learning from a prompted teacher motivates our approach. We observe that this is a special case of context distillation and leverage this observation to show that, in theory, the prompted subliminal learning dataset identifies the teacher's prompt. We reduce recovering this prompt to a text optimization problem and present a method to approximately solve it. Our method, SALVE (Search-Aided Latent Verbalization), optimizes a soft prompt, queries the same model to verbalize it as text, and uses beam search to make the verbalization reliable. In the standard subliminal learning setting, SALVE reliably recovers legible prompts that name the teacher's trait, while common text optimization methods fail to do so. In addition, we find that there are settings in which SALVE recovers the teacher's trait from a dataset even when subliminal learning fails, but that modifying student training to improve context distillation can create subliminal learning effects. We lastly show that SALVE detects subliminal learning effects in three additional settings: (1) mixtures of subliminal learning data and unrelated data, (2) data generated when the teacher is biased via activation steering, and (3) subsets of real preference data selected via Logit-Linear Selection. Overall, our results deepen our understanding of subliminal learning and present SALVE as a method to proactively detect subliminal learning effects.

In this reproduction paper we investigate subliminal learning, a consequence of distillation where teacher models transmit behavioral preference traits through semantically unrelated data. The original paper explores two types of traits (animal preferences and misalignment), three data modalities (number sequences, code, and chain of thought), and several model families. We reproduce their experiments and extend the setup along three axes: new preference categories (actors and politicians), a new task (chess move generation), and an additional open-weight model (Ministral8B). We also run a controlled ablation on the numbers task's answer-space size (1-, 2-, and 3-digit sequences). We focus on open-weight models with accessible checkpoints on HuggingFace, since the original paper's GPT-4.x fine-tuning is no longer available. Our reproduction supports the original paper's claims, but our extensions show they are not universal as transmission strength varies across traits and tasks, and one model shows almost no effect at all.

Beyond intended capabilities, model distillation can transfer hidden traits from a teacher. 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, a phenomenon known as subliminal learning. Prior work has identified several parts of this process. How the signal builds up during training and produces behavioral transfer remains unclear, making targeted mitigation difficult. We propose and validate trait-direction drift as a mechanism for subliminal learning: biased generation creates measurable preference gaps in teacher data, and student-recognizable gaps induce trait-aligned updates during supervised fine-tuning that accumulate into behavioral transfer. Guided by this mechanism, we propose probe-space corridor regularization, a targeted defense that constrains drift along a calibrated trait direction during distillation. The method substantially reduces hidden-trait transfer, preserving task performance: for example, it lowers malicious-response transfer from 29.55% to 6.45% with low main-task accuracy cost, and consistently suppresses animal-preference transfer across the main Qwen setting. The preference-gap, training-trajectory, and intervention evidence links subliminal learning to trait-direction drift and motivates corridor regularization as a targeted control during distillation.

Subliminal Learning (SL) is a surprising type of generalization displayed by modern language models. 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 from the teacher. This presents challenges in ensuring AI systems remain predictable and are trained safely, as standard auditing of the input data would not catch the hidden subliminal signal. Here, we investigate several open questions as to the enabling mechanisms and drivers of SL. First is the nature of the process by which biases are encoded in the data. We find that by adding Gaussian noise to the weights of the teacher and student models, the magnitude of subliminal transfer is increased by a factor of 1.9 in Gemma and 1.3 in Llama, suggesting that non-semantic weight structures play a crucial role. We show that steering vectors can be applied to the teacher to produce subliminal data, in addition to prompting and finetuning as used in previous studies. Analysis of the activations of the student models that have been trained on steered and prompted data demonstrates that students inherit not just the semantic meaning of the teacher's bias, but also the type of intervention that was used to apply it: steered students imitate steering vectors, prompted students do not. Additionally, the gradients of steered subliminal data show a linear correlation with the teacher's steering vectors, showing promise for data auditing. More broadly, as synthetic data becomes central to frontier training pipelines, being able to see the latent signals hidden in training data becomes paramount.

Subliminal learning lets a student inherit a teacher's hidden trait from distillation data that never names it. We ask when such transfer can be audited before training. The answer is not model identity or scale alone, but channel location: the carrier through which the trait reaches the student. We find three regimes. In a controlled initialization-dependent body channel, a pre-training screen works. Coverage, the cosine between the student's initial distillation update and the teacher's fine-tuning displacement, predicts held-out transfer (Spearman $ρ\approx 0.95$; AUROC 0.997). In pretrained language models, masked single-token traits instead ride convergent vocabulary geometry. This channel is initialization-independent, so initialization-alignment screens, including coverage, are not mechanistic; the useful handles are post-hoc detection and targeted mitigation. Even when a single-token named entity is removed from the loss, the student's held-out probability for that entity rises to 0.40 on average ($\sim 2500\times$), and a related semantic class transfers. In an untied-head model, orthogonalizing the trait's output row against entangled neighbours collapses leakage, while equal-size random-subspace edits do not. Thus removing a target string from distillation labels does not remove the corresponding preference: neighbouring tokens can carry it. Finally, conditional behaviours can route through the network body. For sycophancy, with agreement and correction markers masked from the loss, transfer reaches about 0.63 of the teacher's effect, localizes to body computation, and evades four audits across two model families. We scope this as masked transfer of a condition-present policy. Channel location is necessary for deciding which audits can be sound. It is not a deployment-ready screen: an audit used outside its carrier regime can give false assurance.

Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning. While qualitative evidence supports the existence of this effect, its magnitude has not been systematically characterized. This study quantifies subliminal behavioral transfer ratios by steering two teacher models (Llama-2-7B-Chat and Qwen2.5-7B-Instruct) at varying steering strengths and distilling student models using only benign data. Evaluation on 100 JailbreakBench prompts with GPT-4.1, serving as the evaluator, indicates that transfer is robust but exhibits distinct scaling behaviors. Llama-2 demonstrates a sharp threshold ($τ= {0.25,0.32} \ \text{beyond} \ α= -0.15$), whereas Qwen2.5 displays continuous and higher levels of transfer ($τ$ up to $0.61$).

Subliminal learning refers to a student language model acquiring a teacher's traits (e.g. a system-prompted preference for owls) when fine-tuned on the teacher's outputs, despite the outputs being semantically unrelated to those traits. It remains poorly understood how data without semantic meaning can transfer specific semantic traits. In this work, we show that subliminal learning is mediated by a single steering vector, i.e. a vector added to the model's activations. Across two open-source models, we find that the teacher's system prompt is well approximated by a steering vector, and that the student's behavior is driven by learning an aligned vector over fine-tuning. System prompts that are not well approximated by steering vectors are not subliminally learned. This is a special case of steering vector distillation, in which a student trained on the outputs of a steered teacher learns to imitate that steering. We demonstrate steering vector distillation on a range of semantic and random vectors. Adding a semantic vector to a model's activations can have both model-independent and model-specific (i.e. non-semantic) effects on its behavior, so generated data that is non-semantic can transmit a vector with semantic effects, enabling subliminal learning. This also explains why subliminal learning does not transfer between models. We find that adaptive optimizers are necessary for subliminal learning in language models: activation gradients on steered data carry a small but consistent component along the steering direction, and non-adaptive optimizers impede this by allowing outlier gradients to dominate.

Subliminal learning is a phenomenon where language models can transmit behavioral traits to other models through seemingly innocuous data (Cloud et al., 2025). In subliminal learning, a teacher model with a behavioral trait (e.g. obsession with cats) can transmit this cat obsession to a student model finetuned only on numerical sequences generated by the teacher. In this paper, we ask: how does this unexpected behavioral transmission occur? We show that subliminal learning is a LoRA artifact. When subliminal learning occurs, transmission has an inverted U-shaped relationship with LoRA rank; it also disappears with full finetuning. We show that subliminal learning is highly dependent on the context seen during finetuning and evaluation. For example, a Qwen model with the default system prompt during finetuning ("You are Qwen, created by Alibaba Cloud. You are a helpful assistant.") does not show subliminal learning during generation when no system prompt is included. We further demonstrate that subliminal behavior is localized to computation at tokens seen during both finetuning and evaluation (e.g. the model's default system prompt, the standard chat template tokens, etc.). Overall, subliminal learning seems to be a fragile artifact of LoRA hyperparameters and finetuning context, making it an unstable channel for behavioral transmission.

In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher to student models through distillation on task-unrelated input$\unicode{x2013}$output pairs. Prior explanations tie this effect to shared or closely matched teacher$\unicode{x2013}$student initialization. We show that a closely matched initialization is not necessary. Instead, subliminal learning is governed by compatible output heads. Using a controlled MNIST setting, we split outputs into an auxiliary head (for auxiliary, task-unrelated noise signals) and a class head (for classification) to demonstrate subliminal learning occurs$\unicode{x2014}$even when we randomly initialize hidden layers and remove layers, add new layers, or change the architecture (MLP-to-CNN). Compatible auxiliary heads enable transfer of a recoverable teacher signal, bringing the student's representations closer to the teacher's. When the class heads remain compatible as well, students trained only on task-unrelated noise can approach, and in favorable regimes match, teacher-level task performance. Our setting enables us to develop a theory that explains the mechanism of subliminal learning and to derive upper bounds on when subliminal learning fails. Together, our results turn subliminal learning from a surprising transfer effect into a theoretically grounded mechanism with predictable limits.

Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning distribution. We argue that emergent misalignment can be better understood as a data-mediated transfer phenomenon: harmful fine-tuning examples do not induce uniform behavioral spillover, but interact with the structural properties of the dataset and the difficulty of the tasks relative to the model. Across our experiments, we find that misalignment appears more readily when fine-tuning and evaluation prompts share similar underlying functional structure, when prompts leave more room for coherent harmful completions, and when the target behavior has been more reliably learned by the model. The training pipeline itself also matters: pretraining composition shapes later misalignment. We further study Subliminal Learning (SL), where misalignment is transmitted by fine-tuning on seemingly benign data generated by a harmful teacher. Moving beyond the standard SFT setting, we for the first time compare this transfer under off-policy and on-policy distillation as well, allowing us to separate the roles of the teacher guidance and the training data distribution in transmitting misalignment. Together, these results argue for a data-centric view: Emergent/subliminal misalignment should not be treated as a simple consequence of isolated harmful fine-tuning examples, but as the result of interactions between fine-tuning data structure, pretraining distributions, and training channels.

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.

In the MNIST auxiliary logit distillation experiment, a student can acquire an unintended teacher trait despite distilling only on no-class logits through a phenomenon called subliminal learning. Under a single-step gradient descent assumption, subliminal learning theory attributes this effect to alignment between the trait and distillation gradients, but does not guarantee that this alignment persists in a multi-step setting. We empirically show that gradient alignment remains weakly but consistently positive throughout training and causally contributes to trait acquisition. We show that a mitigation method called liminal training works by attenuating the alignment and fails to stop trait acquisition in this setup. These results suggest that mitigation methods that operate in this regime may not reliably suppress trait acquisition when the first-order drive dominates.

Recent work on subliminal learning demonstrates that language models can transmit semantic traits through data that is semantically unrelated to those traits. However, it remains unclear whether behavioral traits can transfer in agentic systems, where policies are learned from trajectories rather than static text. In this work, we provide the first empirical evidence that unsafe agent behaviors can transfer subliminally through model distillation across two complementary experimental settings. In our primary setting, we construct a teacher agent exhibiting a strong deletion bias, a tendency to perform destructive file-system actions via an API-style tool interface, and distill it into a student using only trajectories from ostensibly safe tasks, with all explicit deletion keywords rigorously filtered. In our secondary setting, we replicate the threat model in a native Bash environment, replacing API tool calls with shell commands and operationalizing the bias as a preference for issuing chmod as the first permission-related command over semantically equivalent alternatives such as chown or setfacl. Despite full keyword sanitation in both settings, students inherit measurable behavioral biases. In the API setting the student's deletion rate reaches 100% (versus a 5% baseline) under homogeneous distillation; in the Bash setting the student's chmod-first rate reaches 30%-55% (versus a 0%-10% baseline), with the strongest transfer observed in large-to-small distillation. Our results demonstrate that explicit data sanitation is an insufficient defense, and behavioral biases are encoded implicitly in trajectory dynamics regardless of the tool interface.