Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Verbalizing Subliminal Learning Effects Using Text Optimization
Nathan Hu, Sanmi Koyejo, Christopher Potts
Subliminal learning is a phenomenon in which a distillation dataset transmits traits from the teacher model that are not legibly encoded in the dataset itself. This introduces a ne…
cs.LG2026
Transcoder Adapters for Reasoning-Model Diffing
Nathan Hu, Jake Ward, Thomas Icard +1
While reasoning models are increasingly ubiquitous, the effects of reasoning training on a model's internal mechanisms remain poorly understood. In this work, we introduce transcod…