A Step Towards Forgetting: Optimiser History and the Loss of Answer Mass
During fine-tuning, a language model can assign less probability to previously learned answers even when the current gradient acts to preserve that probability.
By Valeria Ruscio, Seth Nabarro, Keiran ThompsonarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 6, 2026.
Comments
Sign in to join the discussion.