@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-zhang-2026-cake">
<titleInfo>
<title>CAKE: Causal-Guided Adaptive Knowledge Editing for LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuxin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianhao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<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 CAKE (Causal-Guided Adaptive Knowledge Editing), 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.</abstract>
<identifier type="citekey">liu-zhang-2026-cake</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.918/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>20040</start>
<end>20070</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAKE: Causal-Guided Adaptive Knowledge Editing for LLMs
%A Liu, Shuxin
%A Zhang, Jianhao
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F liu-zhang-2026-cake
%X 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 CAKE (Causal-Guided Adaptive Knowledge Editing), 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.
%U https://aclanthology.org/2026.acl-long.918/
%P 20040-20070
Markdown (Informal)
[CAKE: Causal-Guided Adaptive Knowledge Editing for LLMs](https://aclanthology.org/2026.acl-long.918/) (Liu & Zhang, ACL 2026)
ACL
- Shuxin Liu and Jianhao Zhang. 2026. CAKE: Causal-Guided Adaptive Knowledge Editing for LLMs. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 20040–20070, San Diego, California, United States. Association for Computational Linguistics.