Multi-hop Question Answering under Temporal Knowledge Editing
This work addresses a specific limitation in multi-hop QA for temporal knowledge editing, providing an incremental improvement with a new benchmark.
The paper tackles the problem of multi-hop question answering under knowledge editing when questions contain explicit temporal contexts, proposing TEMPLE-MQA, which outperforms baseline models on benchmark datasets and introduces a new dataset TKEMQA for this task.
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.