Multi-hop Question Answering under Temporal Knowledge Editing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910392828035072 |
|---|---|
| author | Cheng, Keyuan Lin, Gang Fei, Haoyang zhai, Yuxuan Yu, Lu Ali, Muhammad Asif Hu, Lijie Wang, Di |
| author_facet | Cheng, Keyuan Lin, Gang Fei, Haoyang zhai, Yuxuan Yu, Lu Ali, Muhammad Asif Hu, Lijie Wang, Di |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00492 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-hop Question Answering under Temporal Knowledge Editing Cheng, Keyuan Lin, Gang Fei, Haoyang zhai, Yuxuan Yu, Lu Ali, Muhammad Asif Hu, Lijie Wang, Di Computation and Language Artificial Intelligence Machine Learning 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. |
| title | Multi-hop Question Answering under Temporal Knowledge Editing |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2404.00492 |