An attribution-based continual learning framework for LLMs modulates per-parameter gradients using task-specific importance scores to reduce forgetting of prior tasks.
Sapt: A shared attention framework for parameter-efficient continual learning of large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Attribution-Guided Continual Learning for Large Language Models
An attribution-based continual learning framework for LLMs modulates per-parameter gradients using task-specific importance scores to reduce forgetting of prior tasks.