@inproceedings{si-etal-2026-mitigating,
    title = "Mitigating Structural Knowledge Collapse in Domain-Specific {LLM}s via Morpheme-Aware {KV}-Aggregation",
    author = "Si, Yuxuan  and
      Lv, Zheqi  and
      Zang, Chengxi  and
      Chen, Zhengyu  and
      Wu, Fei",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1355/",
    pages = "29399--29413",
    ISBN = "979-8-89176-390-6",
    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 Morpheme Aggregation (IMA) and Context-Aware KV-Aggregation (AMRF), to stabilize morpheme 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. Moreover, MorphKA reduces catastrophic interference on general capabilities by 18{--}22{\%} with {\textasciitilde}80{\%} fewer parameters than embedding retraining approaches."
}