SOURCE-LINKED INTELLIGENCE

CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Supervised fine-tuning (SFT) is the de facto standard for adapting large language models (LLMs) to target domains, but it often degrades the model's general capabilities, a phenomenon known as catastrophic forgetting. Existing approaches typically modify the SFT loss to mitigate forgetting, but they inevitably operate along a domain-generality trade-off. In this work, we step outside this trade-off by decoupling the two capabilities at the model level: we keep the original base model for general capability, and selectively invoke the SFT expert only when domain-specific knowledge is required.

Read original source ↗ Open in workspace

recordType

paper

region

Global