LRP-derived element-wise parameter importance scores gate gradients so parameters critical to earlier tasks receive smaller updates during continual LLM fine-tuning.
Copr: Continual learn- ing human preference through optimal policy regularization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attribution-Guided Continual Learning for Large Language Models
LRP-derived element-wise parameter importance scores gate gradients so parameters critical to earlier tasks receive smaller updates during continual LLM fine-tuning.