LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning
Adaptive Unlearning is presented, a post-deployment framework that surgically suppresses package hallucinations while preserving general model utility and relies entirely on model-generated data and requires no human annotation, representing a post-deployment hallucination mitigation framework.
Joseph Spracklen, Pedram Aghazadeh, F. Koushanfar et al.
· 0 citations