1 citations · 2 across the 7 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment
Chengting Yu, Fengzhao Zhang, Ruizhe Chen +4
Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits…
cs.LG2024
Learnable Privacy Neurons Localization in Language Models
Ruizhe Chen, Tianxiang Hu, Yang Feng +1
Concerns regarding Large Language Models (LLMs) to memorize and disclose private information, particularly Personally Identifiable Information (PII), become prominent within the co…