Multi-hop Question Answering under Temporal Knowledge Editing
Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing models for MQA under KE exhibit poor performance when dealing with questions containing explicit temporal contexts. To address this limitation, we...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
30.03.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing models for MQA under KE exhibit poor performance when dealing with questions containing explicit temporal contexts. To address this limitation, we propose a novel framework, namely TEMPoral knowLEdge augmented Multi-hop Question Answering (TEMPLE-MQA). Unlike previous methods, TEMPLE-MQA first constructs a time-aware graph (TAG) to store edit knowledge in a structured manner. Then, through our proposed inference path, structural retrieval, and joint reasoning stages, TEMPLE-MQA effectively discerns temporal contexts within the question query. Experiments on benchmark datasets demonstrate that TEMPLE-MQA significantly outperforms baseline models. Additionally, we contribute a new dataset, namely TKEMQA, which serves as the inaugural benchmark tailored specifically for MQA with temporal scopes. |
---|---|
AbstractList | Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing models for MQA under KE exhibit poor performance when dealing with questions containing explicit temporal contexts. To address this limitation, we propose a novel framework, namely TEMPoral knowLEdge augmented Multi-hop Question Answering (TEMPLE-MQA). Unlike previous methods, TEMPLE-MQA first constructs a time-aware graph (TAG) to store edit knowledge in a structured manner. Then, through our proposed inference path, structural retrieval, and joint reasoning stages, TEMPLE-MQA effectively discerns temporal contexts within the question query. Experiments on benchmark datasets demonstrate that TEMPLE-MQA significantly outperforms baseline models. Additionally, we contribute a new dataset, namely TKEMQA, which serves as the inaugural benchmark tailored specifically for MQA with temporal scopes. |
Author | Cheng, Keyuan zhai, Yuxuan Lin, Gang Wang, Di Haoyang Fei Lu, Yu Ali, Muhammad Asif Hu, Lijie |
Author_xml | – sequence: 1 givenname: Keyuan surname: Cheng fullname: Cheng, Keyuan – sequence: 2 givenname: Gang surname: Lin fullname: Lin, Gang – sequence: 3 fullname: Haoyang Fei – sequence: 4 givenname: Yuxuan surname: zhai fullname: zhai, Yuxuan – sequence: 5 givenname: Yu surname: Lu fullname: Lu, Yu – sequence: 6 givenname: Muhammad surname: Ali middlename: Asif fullname: Ali, Muhammad Asif – sequence: 7 givenname: Lijie surname: Hu fullname: Hu, Lijie – sequence: 8 givenname: Di surname: Wang fullname: Wang, Di |
BookMark | eNqNjEEKwjAQAIMoWLV_CHguxKytevAgogjiQei9FLrWlLhbk4Z-3wo-wNMcZpiZGBMTjkSkAVbJdq31VMTeN0opnW10mkIk9rdgO5M8uZX3gL4zTPJAvkdnqJaBKnQyx1fLrrTyStxbrGqUp8p0Q7AQk0dpPcY_zsXyfMqPl6R1_P7uioaDo0EVoEDtUqUhg_-qD9ZsOck |
ContentType | Paper |
Copyright | 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_30309502363 |
IEDL.DBID | 8FG |
IngestDate | Thu Oct 10 16:37:30 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_30309502363 |
OpenAccessLink | https://www.proquest.com/docview/3030950236?pq-origsite=%requestingapplication% |
PQID | 3030950236 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_3030950236 |
PublicationCentury | 2000 |
PublicationDate | 20240330 |
PublicationDateYYYYMMDD | 2024-03-30 |
PublicationDate_xml | – month: 03 year: 2024 text: 20240330 day: 30 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2024 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.537128 |
SecondaryResourceType | preprint |
Snippet | Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Benchmarks Datasets Editing Large language models Questions |
Title | Multi-hop Question Answering under Temporal Knowledge Editing |
URI | https://www.proquest.com/docview/3030950236 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1NSwMxEB20i-DNT_yoJaDX4GaTRjyIqOxalJYiFXor2cwsCtKuuxVv_naTuKsHoccQSMgQ5iVvZt4AnBVoLSlKuDCCuEKluLE58hjRImqTF4GHHI704Fk9TPvThnCrm7TK1icGR40L6znyc-ljAX2vd35dvnPfNcpHV5sWGusQCa-E5yvFs_tfjiXRF-7FLP-52YAd2RZEY1NStQ1rNN-BjZByaetduAq1r_xlUbLAOjoDsZt5_Rm0AZmv7arY5Ec46o09ttQXS_HVZyrvwWmWTu4GvN1z1tyKevZ3BrkPHfe9pwNgiAatFmRjUahLiTk5WDZEBakkNloeQnfVSkerp49hM3EwHKro4i50ltUHnTgYXea9YKseRLfpaPzkRsOv9BtzpH-J |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8QwEB60RfTmEx-rBvQa7CNb9SCi0qW6u2WRCnsraWaKguzWdsW_bxJbPQh7DiRkCPNNvpn5BuC8RKVIUMB96RMXKASXqkDuISrESBal5SHHaZS8iKdpf9oSbk1bVtn5ROuoca4MR34RmlxA3-id31Yf3EyNMtnVdoTGKrhGcvPKAfc-TifPvyxLEF3qmDn852gtegw2wZ3IiuotWKHZNqzZokvV7MCN7X7lr_OKWd5Rm4jdzZovqw7ITHdXzbIf6ah3NuzILxbjm6lV3oWzQZw9JLw7M2_fRZP_3SLcA0d_8GkfGKJEFfmkPL8U1yEWpIFZEpUkAk9G4QH0lu10uHz5FNaTbDzKR4_p8Ag2Ag3KtqfO64GzqD_pWIPqojhpLfcNu_-BFQ |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Multi-hop+Question+Answering+under+Temporal+Knowledge+Editing&rft.jtitle=arXiv.org&rft.au=Cheng%2C+Keyuan&rft.au=Lin%2C+Gang&rft.au=Haoyang+Fei&rft.au=zhai%2C+Yuxuan&rft.date=2024-03-30&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |