@inproceedings{xu-etal-2023-language-anisotropic,
title = "Language Anisotropic Cross-Lingual Model Editing",
author = "Xu, Yang and
Hou, Yutai and
Che, Wanxiang and
Zhang, Min",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.343/",
doi = "10.18653/v1/2023.findings-acl.343",
pages = "5554--5569",
abstract = "Multilingual pre-trained language models can learn task-specific abilities or memorize facts across multiple languages but inevitably make undesired predictions with specific inputs. Under similar observation, model editing aims to post-hoc calibrate a model targeted to specific inputs with keeping the model`s raw behavior. However, existing work only studies the monolingual scenario, which lacks the cross-lingual transferability to perform editing simultaneously across languages. In this work, we focus on cross-lingual model editing. Firstly, we define the cross-lingual model editing task and corresponding metrics, where an edit in one language propagates to the others. Next, we propose a framework to naturally adapt monolingual model editing approaches to the cross-lingual scenario using parallel corpus. Further, we propose language anisotropic editing to improve cross-lingual editing by amplifying different subsets of parameters for each language. On the newly defined cross-lingual model editing task, we empirically demonstrate the failure of monolingual baselines in propagating the edit to multiple languages and the effectiveness of the proposed language anisotropic model editing. Our code is publicly available at \url{https://github.com/franklear/LiME}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-language-anisotropic">
<titleInfo>
<title>Language Anisotropic Cross-Lingual Model Editing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutai</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual pre-trained language models can learn task-specific abilities or memorize facts across multiple languages but inevitably make undesired predictions with specific inputs. Under similar observation, model editing aims to post-hoc calibrate a model targeted to specific inputs with keeping the model‘s raw behavior. However, existing work only studies the monolingual scenario, which lacks the cross-lingual transferability to perform editing simultaneously across languages. In this work, we focus on cross-lingual model editing. Firstly, we define the cross-lingual model editing task and corresponding metrics, where an edit in one language propagates to the others. Next, we propose a framework to naturally adapt monolingual model editing approaches to the cross-lingual scenario using parallel corpus. Further, we propose language anisotropic editing to improve cross-lingual editing by amplifying different subsets of parameters for each language. On the newly defined cross-lingual model editing task, we empirically demonstrate the failure of monolingual baselines in propagating the edit to multiple languages and the effectiveness of the proposed language anisotropic model editing. Our code is publicly available at https://github.com/franklear/LiME.</abstract>
<identifier type="citekey">xu-etal-2023-language-anisotropic</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.343</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.343/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>5554</start>
<end>5569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Anisotropic Cross-Lingual Model Editing
%A Xu, Yang
%A Hou, Yutai
%A Che, Wanxiang
%A Zhang, Min
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F xu-etal-2023-language-anisotropic
%X Multilingual pre-trained language models can learn task-specific abilities or memorize facts across multiple languages but inevitably make undesired predictions with specific inputs. Under similar observation, model editing aims to post-hoc calibrate a model targeted to specific inputs with keeping the model‘s raw behavior. However, existing work only studies the monolingual scenario, which lacks the cross-lingual transferability to perform editing simultaneously across languages. In this work, we focus on cross-lingual model editing. Firstly, we define the cross-lingual model editing task and corresponding metrics, where an edit in one language propagates to the others. Next, we propose a framework to naturally adapt monolingual model editing approaches to the cross-lingual scenario using parallel corpus. Further, we propose language anisotropic editing to improve cross-lingual editing by amplifying different subsets of parameters for each language. On the newly defined cross-lingual model editing task, we empirically demonstrate the failure of monolingual baselines in propagating the edit to multiple languages and the effectiveness of the proposed language anisotropic model editing. Our code is publicly available at https://github.com/franklear/LiME.
%R 10.18653/v1/2023.findings-acl.343
%U https://aclanthology.org/2023.findings-acl.343/
%U https://doi.org/10.18653/v1/2023.findings-acl.343
%P 5554-5569
Markdown (Informal)
[Language Anisotropic Cross-Lingual Model Editing](https://aclanthology.org/2023.findings-acl.343/) (Xu et al., Findings 2023)
ACL
- Yang Xu, Yutai Hou, Wanxiang Che, and Min Zhang. 2023. Language Anisotropic Cross-Lingual Model Editing. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5554–5569, Toronto, Canada. Association for Computational Linguistics.