Tag
This paper investigates cross-model memory transfer, demonstrating that target-side reader adaptation is crucial for utilizing frozen memory tables across different large language models. It introduces methods for reusable knowledge artifacts with optional adaptation to improve alignment.
ReLoRA is a knowledge-reusing adaptation framework that efficiently restores service-ready LoRA adapters for evolving LLM services, reducing time-to-readiness by up to 8.9× and improving accuracy by up to 4.6% through adaptive initialization and scheduled regularization.