SOURCE-LINKED INTELLIGENCE

When to Adapt: Conditional Memory Adapters for Retention-Preserving Domain Specialization

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Large language models deployed in specialized domains must improve in-domain performance without sacrificing general capabilities. Existing parameter-efficient fine-tuning methods are typically always on: their learned perturbations are applied to every input, which can degrade out-of-domain (OOD) performance. We propose Engram Adapter, a framework that repurposes pretraining-time conditional memory as a post-hoc adapter for frozen LLMs. It uses multi-channel matching over local n-gram patterns with explicit occupancy tracking as a lightweight selectivity prior, making residual injection more

Read original source ↗ Open in workspace

recordType

paper

region

Global