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.
By Angela Tang, Vishesh Anand, Gon\c{c}alo Paulo
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.
By Zhixuan Liu, Zhichen Dong, Yuyu Fan, Xiangtian Li, Chao Yang
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.
By Joseph Egan, Ciar\'{a}n M. Gilligan-Lee, Michael O'Riordan, Yuchen Zhu
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...
By Atsushi Yanagisawa, Brendan Gho, Rajendran Ramesh Babu Manoj Narender, Kevin Zhu, Madhur Panwar, Antonio Mari
The paper introduces two distillation methods for handling misaligned AI models. Distillation for Incrimination (DFI) transfers misalignment without the ability to conceal it, making students more likely to admit hidden behaviors. Distillation for Capabilities (DFC) transfers useful capabilities while minimizing misalignment, using techniques like inoculation prompting and focused training.
By Sebastian Prasanna, Jacqueline Tay, Alek Westover
arXiv:2606. 11270v1 Announce Type: cross Abstract: 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.
By Uwe Konig, Hamza Kazmi, Ruizhe Li, Maheep Chaudhary
The paper investigates whether subliminal learning (SL) can transfer a broader set of traits beyond simple preferences, such as complex capabilities, backdoors, and hacking tendencies. Experiments show that SL can indeed impart a student model with the ability to predict outputs of a random MLP, partially embed a backdoor that triggers French responses to female names, and increase hacking success in a chess environment. The effectiveness of transfer varies with the distillation method, being enhanced by logit distillation or limiting LoRA to attention layers.
By Jan Dubi\'nski, Anna Sztyber-Betley, Jan Betley, Owain Evans
arXiv:2608.20442v1 Announce Type: new
Abstract: Subliminal trait transfer allows a student model to acquire behavioral dispositions from teacher-generated data in which the trait is not semantically...
By Qinyang Xu
arXiv:2606. 00995v1 Announce Type: new Abstract: Subliminal learning refers to a student language model acquiring a teacher's traits (e.
By Camila Blank, Agam Bhatia, Senthooran Rajamanoharan, Arthur Conmy, Neel Nanda
The paper investigates how on-policy self‑distillation can alter a model’s behavior by conditioning on privileged information. It contrasts attractive self‑distillation, which pulls a model toward a privileged teacher, with repulsive self‑distillation, which pushes it away, showing that attraction reduces exploratory reasoning while repulsion lengthens responses and can destabilize the model. The authors propose a contrastive self‑distillation objective that combines attraction to a correct‑solution teacher with repulsion from an incorrect‑solution teacher, finding that this approach improves reasoning performance across various model types while keeping response lengths stable.
By Anton Baumann, Akmal Ashirmatov, Leo Schmidt-Traub, Frederike L\"ubeck, Jonas H\"ubotter, Thomas Kleine Buening, Andreas Krause
Language models trained on the outputs of other models can acquire traits that those outputs never mention, such as a preference for an animal carried by lists of numbers. Such subliminal learning can...
arXiv:2607. 09692v1 Announce Type: new Abstract: Model distillation -- training on outputs from stronger third-party models -- is widely used to boost performance, but raises concerns about unfair advantages and policy violations.
By Rajat Rawat, Sizhe Chen, Akshay Anand, Michael Duan, Bob Rotsted, Sewon Min