Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models
Hayder Elesedy, Pedro M. Esperança, Silviu Vlad Oprea +1
Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for res…
cs.LG2019
Fine-grained Optimization of Deep Neural Networks
Mete Ozay
In recent studies, several asymptotic upper bounds on generalization errors on deep neural networks (DNNs) are theoretically derived. These bounds are functions of several norms of…