Papers by Thao Minh Le
Continual Safety Alignment via Gradient-Based Sample Selection (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models require continuous adaptation to new domains, tasks, and evolving requirements. |
| Approach: | They propose a gradient-based sample selection method that filters high-gradient samples during fine-tuning. |
| Outcome: | The proposed method significantly improves alignment preservation while maintaining competitive task performance on continual domain tasks. |