Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan
Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominantly rely o…
cs.LG2025
EDoRA: Efficient Weight-Decomposed Low-Rank Adaptation via Singular Value Decomposition
Hamid Nasiri, Peter Garraghan
Parameter-efficient fine-tuning methods, such as LoRA, reduces the number of trainable parameters. However, they often suffer from scalability issues and differences between their…