Where to Adapt Matters: Layer-Selective Fine-Tuning for Capability Retention
Parameter-efficient fine-tuning (PEFT) enables large language models (LLMs) to adapt to specialized tasks, but often at the cost of degrading general capabilities acquired during pretraining. Existing approaches primarily mitigate this trade-off through data replay or regularization, relying on additional data or explicit optimization constraints. We instead focus on a different question: where…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
Source: arxiv.org