@inproceedings{qiao-etal-2024-distillmike,
title = "{D}istill{MIKE}: Editing Distillation of Massive In-Context Knowledge Editing in Large Language Models",
author = "Qiao, Shanbao and
Liu, Xuebing and
Na, Seung-Hoon",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.455",
doi = "10.18653/v1/2024.findings-acl.455",
pages = "7639--7654",
abstract = "Among the recently emerged knowledge editing methods, in-context knowledge editing (IKE) has shown respectable abilities on knowledge editing in terms of generalization and specificity. Noting the promising advantages but unexplored issues of IKE, we propose **DistillMIKE** as a novel extension of IKE, i.e., editing **distill**ation of ''**M**assive{''} **I**n-context **K**nowledge **E**diting in large language models (LLMs), mainly consisting of two expansions; 1) *Massive in-context knowledge editing (MIKE)*, which extends IKE to a massive editing task, aiming to inject not a single edit but a set of massive edits to LLMs; To preserve specificity, our key novel extension is a {``}selective{''} retrieval augmentation, where the retrieval-augmented IKE is only applied to {``}in-scope{''} examples, whereas the unedited model without IKE is employed for {``}out-of-scope{''} ones. 2) *Editing distillation* of MIKE using low-rank adaptation (LoRA), which distills editing abilities of MIKE to parameters of LLMs in a manner of eliminating the need of lengthy in-context demonstrations, thus removing the computational overhead encountered at the inference time. Experimental results on the zsRE and CounterFact datasets demonstrate that MIKE shows the state-of-the-art perfomrances and DistilMIKE show comparable performances with MIKE. Our code is available at https://github.com/JoveReCode/DistillMIKE.git.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiao-etal-2024-distillmike">
<titleInfo>
<title>DistillMIKE: Editing Distillation of Massive In-Context Knowledge Editing in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shanbao</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuebing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Among the recently emerged knowledge editing methods, in-context knowledge editing (IKE) has shown respectable abilities on knowledge editing in terms of generalization and specificity. Noting the promising advantages but unexplored issues of IKE, we propose **DistillMIKE** as a novel extension of IKE, i.e., editing **distill**ation of ”**M**assive” **I**n-context **K**nowledge **E**diting in large language models (LLMs), mainly consisting of two expansions; 1) *Massive in-context knowledge editing (MIKE)*, which extends IKE to a massive editing task, aiming to inject not a single edit but a set of massive edits to LLMs; To preserve specificity, our key novel extension is a “selective” retrieval augmentation, where the retrieval-augmented IKE is only applied to “in-scope” examples, whereas the unedited model without IKE is employed for “out-of-scope” ones. 2) *Editing distillation* of MIKE using low-rank adaptation (LoRA), which distills editing abilities of MIKE to parameters of LLMs in a manner of eliminating the need of lengthy in-context demonstrations, thus removing the computational overhead encountered at the inference time. Experimental results on the zsRE and CounterFact datasets demonstrate that MIKE shows the state-of-the-art perfomrances and DistilMIKE show comparable performances with MIKE. Our code is available at https://github.com/JoveReCode/DistillMIKE.git.</abstract>
<identifier type="citekey">qiao-etal-2024-distillmike</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.455</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.455</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>7639</start>
<end>7654</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DistillMIKE: Editing Distillation of Massive In-Context Knowledge Editing in Large Language Models
%A Qiao, Shanbao
%A Liu, Xuebing
%A Na, Seung-Hoon
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F qiao-etal-2024-distillmike
%X Among the recently emerged knowledge editing methods, in-context knowledge editing (IKE) has shown respectable abilities on knowledge editing in terms of generalization and specificity. Noting the promising advantages but unexplored issues of IKE, we propose **DistillMIKE** as a novel extension of IKE, i.e., editing **distill**ation of ”**M**assive” **I**n-context **K**nowledge **E**diting in large language models (LLMs), mainly consisting of two expansions; 1) *Massive in-context knowledge editing (MIKE)*, which extends IKE to a massive editing task, aiming to inject not a single edit but a set of massive edits to LLMs; To preserve specificity, our key novel extension is a “selective” retrieval augmentation, where the retrieval-augmented IKE is only applied to “in-scope” examples, whereas the unedited model without IKE is employed for “out-of-scope” ones. 2) *Editing distillation* of MIKE using low-rank adaptation (LoRA), which distills editing abilities of MIKE to parameters of LLMs in a manner of eliminating the need of lengthy in-context demonstrations, thus removing the computational overhead encountered at the inference time. Experimental results on the zsRE and CounterFact datasets demonstrate that MIKE shows the state-of-the-art perfomrances and DistilMIKE show comparable performances with MIKE. Our code is available at https://github.com/JoveReCode/DistillMIKE.git.
%R 10.18653/v1/2024.findings-acl.455
%U https://aclanthology.org/2024.findings-acl.455
%U https://doi.org/10.18653/v1/2024.findings-acl.455
%P 7639-7654
Markdown (Informal)
[DistillMIKE: Editing Distillation of Massive In-Context Knowledge Editing in Large Language Models](https://aclanthology.org/2024.findings-acl.455) (Qiao et al., Findings 2024)
ACL