RRDA introduces a router plus separate edit and locality adapters for memory-assisted knowledge editing, reporting highest accuracy on CounterFact, ZsRE, and MQuAKE-CF across two 8B models.
Time sensitive knowledge editing through efficient finetuning.arXiv preprint arXiv:2406.04496
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
Collaborative Parameter Learning freezes 50-75% of parameters whose updates cause forgetting and updates only the 25-50% that mitigate it, allowing LLMs to learn 20-48% more new questions with negligible forgetting and lower compute cost.
citing papers explorer
-
When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing
RRDA introduces a router plus separate edit and locality adapters for memory-assisted knowledge editing, reporting highest accuracy on CounterFact, ZsRE, and MQuAKE-CF across two 8B models.
-
Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis
Collaborative Parameter Learning freezes 50-75% of parameters whose updates cause forgetting and updates only the 25-50% that mitigate it, allowing LLMs to learn 20-48% more new questions with negligible forgetting and lower compute cost.