Mitigating Structural Knowledge Collapse in Domain-Specific LLMs via Morpheme-Aware KV-Aggregation

. Abstract Standard tokenizers over-fragment domain terms, disrupting morpheme semantics. We characterize this representational misalignment as Structural Knowledge Collapse (SKC), where attention mechanisms fail to reconstruct coherent concepts from fragmented inputs. While existing input-centric solutions like vocabulary expansion address this, they necessitate expensive embedding retraining and neglect internal attention compositionality. To this end, we introduce Morpheme-aware KV-aggregation Attention (MorphKA), a lightweight adapter that dynamically consolidates fragments without tokenizer changes. Bypassing tokenizer retraining, MorphKA employs a dual-phase strategy—Input-Level Mor-pheme Aggregation (IMA) and Context-Aware KV-Aggregation (AMRF)—to stabilize mor-pheme spans and synthesize higher-order concepts. Experiments on medical and legal benchmarks show MorphKA outperforms vocabulary adaptation baselines by 3.2–4.6%, reaching 7.9% on high-fragmentation terms. More-over, MorphKA reduces catastrophic interference on general capabilities by 18–22% with ∼ 80% fewer parameters than embedding re-training approaches.