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
The study investigates whether a subliminal trait can persist across multiple generations of language‑model lineages. Three copies of Qwen2.5‑7B‑Instruct were trained for ten iterations, and the trait’s expression was measured via a keyword screen and an activation probe. Results show the trait remains detectable in all generations, though its behavioral expression diminishes, and it can exist internally without being overtly expressed when the system prompt is removed.
By Ryan Vo, Duc-Vu Nguyen, Matt Kretchmar, Ngan Luu-Thuy Nguyen
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
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 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
The paper investigates how scaling the amount of model-generated, off‑task distillation data affects the recoverability of teacher‑induced traits in student models. In a controlled subliminal‑learning setup, teachers are prompted to express a target trait, producing restricted data such as number‑only completions. Students trained on larger independent datasets show a clearer manifestation of the teacher’s trait in a separate evaluation domain, with the effect being strongest when the trait is already favored or when alternative traits are present. The authors find this trend holds across model families, trait types, multi‑trait settings, and cross‑model transfer, and suggest that scaling should be coupled with trait‑aware curation and evaluation.
By Zhichen Dong, Zhixuan Liu, Yuyu Fan, Xiangtian Li, Shuyang Zhang, Chao Yang
The paper introduces "Subliminal Reinforcement Learning," a method where a model’s traits are transferred through data that contains no explicit semantic cues. Using a language‑model judge that scores the model’s own outputs, the authors demonstrate that a student model can acquire a preference for a particular animal simply by learning from the judge’s scores, even when the student’s outputs are nonsensical syllables or numbers. Across 48 experimental conditions, 17 met a 5% false‑discovery threshold, while removing the reward difference between judges eliminated the transfer effect, establishing a four‑stage chain that explains how traits propagate.
"whyItMatters":"The findings suggest that subtle, non‑semantic signals from evaluators can shape AI behavior, highlighting a potential risk pathway for undesirable dispositions in safety‑critical systems."
By Keuntae Kim, Yong Suk Choi
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 investigates how language models can covertly encode a hidden trait—termed subliminal learning—through seemingly unrelated outputs. By systematically measuring output co‑variation, fixed output‑vector alignment, hidden‑state readability, and causal control across a range of model sizes and prompting protocols, the authors find that fixed geometry and observational readability do not reliably predict behavior, while causal timing and multi‑token measurements reveal stronger, concept‑wide effects. These distinct properties highlight that token‑level explanations are insufficient to pinpoint the mechanism behind training‑time trait transfer.
By Barath Velmurugan
Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ("Sue cried because"), it resolves the next pronoun to she, generalizing to held-out probes (0. 94 by step 925).
arXiv:2606. 26050v1 Announce Type: new Abstract: Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ("Sue cried because"), it resolves the next pronoun to she, generalizing to held-out probes (0.
By Juliana Li, Diya Sreedhar
arXiv:2607. 13162v1 Announce Type: cross Abstract: What a language model will and will not do is largely set during post-training, but which behaviors it expresses, hides, or resists is not revealed by prompting alone.
By Winston Zeng, Ali Emami, Jinho Choi