← Back to all news
arXiv AI By Nathan Hu, Sanmi Koyejo, Christopher Potts

Verbalizing Subliminal Learning Effects Using Text Optimization

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
5d ago

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.

By Moritz Weckbecker, Sweta Jena, Jonas M\"uller, Ponnurangam Kumaraguru, Sebastian Lapuschkin, Wojciech Samek, Louis Jaburi, Gon\c{c}alo Paulo
llmssafety
More like this →
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.

By Zhixuan Liu, Zhichen Dong, Yuyu Fan, Xiangtian Li, Chao Yang
fine-tuningefficiency
More like this →