@inproceedings{liu-zhang-2026-cake,
    title = "{CAKE}: Causal-Guided Adaptive Knowledge Editing for {LLM}s",
    author = "Liu, Shuxin  and
      Zhang, Jianhao",
    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.918/",
    pages = "20040--20070",
    ISBN = "979-8-89176-390-6",
    abstract = "LLMs have static pre-trained knowledge, leading to obsolescence and hallucinations. Knowledge Editing (KE) addresses these issues and typically requires multi-layer modifications. However, existing state-of-the-art methods, largely following the Locate{--}Select{--}Assign{--}Edit (LSAE) paradigm, rely on fixed-layer selection and uniform residual assignment, ignoring the heterogeneous causal efficacy of different layers. To bridge this, we propose $\textbf{CAKE}$ ($\textbf{C}$ausal-Guided $\textbf{A}$daptive $\textbf{K}$nowledge $\textbf{E}$diting), a collaborative editing method within the more general Locate{--}Weight{--}Assign{--}Edit (LWAE) paradigm that: (1) selectively identifies critical layers via causal tracing scores; and (2) adaptively allocates editing burdens based on causal weights rather than uniform assumptions. We formulate residual assignment as a constrained quadratic optimization problem and derive a solution for optimal residual allocation, showing that aligning edits with causal efficacy mitigates recursive error accumulation. Furthermore, we establish a generalized weight shift error bound, under which existing paradigms emerge as special, restricted cases. Experimental results demonstrate that CAKE achieves SOTA performance with comparable overhead, validating the superiority of causal-guided adaptation."
}