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...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Cheng, Keyuan, Lin, Gang, Haoyang Fei, zhai, Yuxuan, Lu, Yu, Ali, Muhammad Asif, Hu, Lijie, Wang, Di
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 30.03.2024
Subjects
Benchmarks
Datasets
Editing
Large language models
Questions
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422