← Back to all news
arXiv AI By Moritz Weckbecker, Sweta Jena, Jonas M\"uller, Ponnurangam Kumaraguru, Sebastian Lapuschkin, Wojciech Samek, Louis Jaburi, Gon\c{c}alo Paulo

Can Data Attribution Filter Out Subliminal Learning? Not Reliably

Read the original on arXiv AI →

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.

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
Sep 16

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.

By Nathan Hu, Sanmi Koyejo, Christopher Potts
efficiency
More like this →
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.

By Joseph Egan, Ciar\'{a}n M. Gilligan-Lee, Michael O'Riordan, Yuchen Zhu
llmsefficiencybenchmarks
More like this →