Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models
- Chia-yi Hsu
- Yu-Lin Tsai
- et al.
- 2024
- NeurIPS 2024
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.