Alleviating the Fear of Losing Alignment in LLM Fine-tuning

Name: Alleviating the Fear of Losing Alignment in LLM Fine-tuning
Duration: 15 min
Description: Talk from IEEE Symposium on Security and Privacy 2025.

Kang Yang, Guanhong Tao, Xun Chen, Jun Xu

IEEE Symposium on Security and Privacy 2025 · Day 2 · ML Defenses