Open-Set Entity Alignment using Large Language Models with Retrieval Augmentation
Linyao Yang, Hongyang Chen, Xiao Wang, Yisheng Lv, Yonglin Tian, Xingyuan Dai, Fei Wang · 2024
Recent years have witnessed remarkable advance-ments in entity alignment, which endeavors to identify entities that represent the same real-world objects across different knowledge graphs (KGs). Nonetheless, prevailing approaches predominantly operate within closed-domain scenarios, rendering them inadequate for handling unmatchable entities. To address this challenge, we propose a retrieval augmented large language model framework (RALLM) to leverage the reasoning capacities of large language models (LLMs) to achieve open-set entity alignment, which not only enables the identification of equivalent entities for matchable entities but also addresses the identification of unmatchable ones. Specifically, we propose a novel retrieval augmentation method that leverages both textual and structural information of entities to retrieve potential equivalent candidates. Subsequently, we employ an iterative process to prompt the LLM to discern the equivalence between the retrieved candidate entity and the entity requiring alignment. To mitigate issues related to many-to-one alignment prediction and enhance alignment efficacy, we devise a memory mechanism to store highly confident aligned entity pairs and provide reminders to the LLM when a candidate entity has been matched. Our experimental findings underscore the superior performance of RALLM, highlighting the potential of LLMs in facilitating open-set entity alignment tasks.