@inproceedings{ali-etal-2025-mqa,
title = "{MQA}-{KEAL}: Multi-hop Question Answering under Knowledge Editing for {A}rabic Language",
author = "Ali, Muhammad Asif and
Daftardar, Nawal and
Waheed, Mutayyba and
Qin, Jianbin and
Wang, Di",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.377/",
pages = "5629--5644",
abstract = "Large Language Models (LLMs) have demonstrated significant capabilities across numerous application domains. A key challenge is to keep these models updated with latest available information, which limits the true potential of these models for the end-applications. Although, there have been numerous attempts for LLMs' Knowledge Editing (KE), i.e., to update and/or edit the LLMs' prior knowledge and in turn test it via Multi-hop Question Answering (MQA), yet so far these studies are primarily focused and/or developed for English language. To bridge this gap, in this paper we propose: Multi-hop Questioning Answering under Knowledge Editing for Arabic Language (MQA-KEAL). MQA-KEAL stores knowledge edits as structured knowledge units in the external memory. In order to solve multi-hop question, it first uses task-decomposition to decompose the question into smaller sub-problems. Later for each sub-problem, it iteratively queries the external memory and/or target LLM in order to generate the final response. In addition, we also contribute MQUAKE-AR (Arabic translation of English benchmark MQUAKE), as well as a new benchmark MQA-AEVAL for rigorous performance evaluation of MQA under KE for Arabic language. Experimentation evaluation reveals MQA-KEAL outperforms the baseline models by a significant margin. We release the codes for MQA-KEAL at https: //github.com/asif6827/MQA-Keal."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ali-etal-2025-mqa">
<titleInfo>
<title>MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Asif</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nawal</namePart>
<namePart type="family">Daftardar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mutayyba</namePart>
<namePart type="family">Waheed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianbin</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have demonstrated significant capabilities across numerous application domains. A key challenge is to keep these models updated with latest available information, which limits the true potential of these models for the end-applications. Although, there have been numerous attempts for LLMs’ Knowledge Editing (KE), i.e., to update and/or edit the LLMs’ prior knowledge and in turn test it via Multi-hop Question Answering (MQA), yet so far these studies are primarily focused and/or developed for English language. To bridge this gap, in this paper we propose: Multi-hop Questioning Answering under Knowledge Editing for Arabic Language (MQA-KEAL). MQA-KEAL stores knowledge edits as structured knowledge units in the external memory. In order to solve multi-hop question, it first uses task-decomposition to decompose the question into smaller sub-problems. Later for each sub-problem, it iteratively queries the external memory and/or target LLM in order to generate the final response. In addition, we also contribute MQUAKE-AR (Arabic translation of English benchmark MQUAKE), as well as a new benchmark MQA-AEVAL for rigorous performance evaluation of MQA under KE for Arabic language. Experimentation evaluation reveals MQA-KEAL outperforms the baseline models by a significant margin. We release the codes for MQA-KEAL at https: //github.com/asif6827/MQA-Keal.</abstract>
<identifier type="citekey">ali-etal-2025-mqa</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.377/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>5629</start>
<end>5644</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language
%A Ali, Muhammad Asif
%A Daftardar, Nawal
%A Waheed, Mutayyba
%A Qin, Jianbin
%A Wang, Di
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F ali-etal-2025-mqa
%X Large Language Models (LLMs) have demonstrated significant capabilities across numerous application domains. A key challenge is to keep these models updated with latest available information, which limits the true potential of these models for the end-applications. Although, there have been numerous attempts for LLMs’ Knowledge Editing (KE), i.e., to update and/or edit the LLMs’ prior knowledge and in turn test it via Multi-hop Question Answering (MQA), yet so far these studies are primarily focused and/or developed for English language. To bridge this gap, in this paper we propose: Multi-hop Questioning Answering under Knowledge Editing for Arabic Language (MQA-KEAL). MQA-KEAL stores knowledge edits as structured knowledge units in the external memory. In order to solve multi-hop question, it first uses task-decomposition to decompose the question into smaller sub-problems. Later for each sub-problem, it iteratively queries the external memory and/or target LLM in order to generate the final response. In addition, we also contribute MQUAKE-AR (Arabic translation of English benchmark MQUAKE), as well as a new benchmark MQA-AEVAL for rigorous performance evaluation of MQA under KE for Arabic language. Experimentation evaluation reveals MQA-KEAL outperforms the baseline models by a significant margin. We release the codes for MQA-KEAL at https: //github.com/asif6827/MQA-Keal.
%U https://aclanthology.org/2025.coling-main.377/
%P 5629-5644
Markdown (Informal)
[MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language](https://aclanthology.org/2025.coling-main.377/) (Ali et al., COLING 2025)
ACL