arXiv AI
Jun 2
Subliminal Learning Is Steering Vector Distillation
arXiv:2606. 00995v1 Announce Type: new Abstract: Subliminal learning refers to a student language model acquiring a teacher's traits (e.
Verbalizing Subliminal Learning Effects Using Text Optimization
The paper introduces SALVE, a method that uses text optimization to uncover and verbalize subliminal learning effects in language models. By optimizing a soft prompt and converting it into a legible text prompt, SALVE can reliably recover the teacher model’s hidden traits that are transmitted through a distillation dataset. The authors demonstrate SALVE’s effectiveness across various scenarios, including mixed datasets, biased teacher activation, and preference‑selected data, thereby providing a tool for detecting hidden influences in model training.
Related stories
arXiv AI
Aug 7
Subliminal Learning is Non-Semantic Distillation
arXiv:2608. 05734v1 Announce Type: new Abstract: Subliminal Learning (SL) is a surprising type of generalization displayed by modern language models.
arXiv Machine Learning
Sep 22
On Mitigation of Subliminal Learning in Large Language Models
arXiv:2609.22215v1 Announce Type: cross Abstract: Knowledge distillation can transmit unintended behavioral traits from a teacher model to a student through training data that appear semantically unr...
Hugging Face Trending Papers
Aug 6
Subliminal Learning is Non-Semantic 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.
arXiv AI
Oct 12
Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning
The paper presents a method for detecting and mitigating subliminally transferred traits in language model distillation when the teacher and student share base parameters. By analyzing parameter updates across diverse datasets, the authors recover a weight‑space direction that reveals hidden traits such as animal preferences, without requiring trait labels. This direction can then be amplified for interpretation or projected out to suppress the trait with minimal impact on task performance.
arXiv AI
Sep 18
Can Data Attribution Filter Out Subliminal Learning? Not Reliably
The paper investigates whether gradient‑based data attribution methods can filter out subliminal learning in language models. Three attribution techniques—GradCos, a contrastive variant, and EK‑FAC—are evaluated on three models and compared to divergence tokens, a strong baseline that requires counterfactual teacher models. Results show that EK‑FAC can mitigate some subliminal effects at the token level, but overall the methods are inconsistent and generally less effective than divergence tokens, especially when filtering entire samples.
arXiv Machine Learning
Sep 2
Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation
The paper investigates subliminal learning, where hidden traits from a teacher model are transferred to a student during distillation. It introduces trait‑direction drift as the underlying mechanism, showing that biased generation creates measurable preference gaps that accumulate into behavioral transfer during fine‑tuning. The authors propose probe‑space corridor regularization, a targeted defense that constrains drift along a calibrated trait direction, significantly reducing hidden‑trait transfer while maintaining task performance.
arXiv AI
Jul 29
Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
arXiv AI
Oct 15
Contrastive Covariance Subspaces for Activation Steering
arXiv:2610.14025v1 Announce Type: cross Abstract: Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, t...
arXiv Machine Learning
Jun 5
Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
arXiv:2603. 19294v4 Announce Type: replace Abstract: While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers.
arXiv Machine Learning
Oct 23
Tracing Subliminal Learning Through Pretraining
The paper investigates subliminal learning, where large language models inherit unintended traits from data generated by other models. It compares hard‑label distillation (students learn from biased teacher outputs) and on‑policy soft‑label distillation (students generate data while teacher logits guide learning), finding that transfer persists across various training conditions and that teacher‑student roles can be asymmetrically effective. Synthetic experiments show that preference signals can be transmitted even without prompt dependence, and that removing certain tokens reduces but does not eliminate transfer, with soft‑label distillation yielding more consistent results with less training.
arXiv AI
Aug 11
DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
arXiv:2605. 15532v3 Announce Type: replace-cross Abstract: Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets.