Defending LLMs against Jailbreaking Attacks via Backtranslation Paper • 2402.16459 • Published Feb 26, 2024 • 4
An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning Paper • 2402.08096 • Published Feb 12, 2024
On the Loss of Context-awareness in General Instruction Fine-tuning Paper • 2411.02688 • Published Nov 5, 2024