Entity Linking (EL) models are well-trained at mapping mentions to their corresponding entities according to a given context. However, EL models struggle to disambiguate long-tail entities due to their limited training data. Meanwhile, large language models (LLMs) are more robust at interpreting uncommon mentions. Yet, due to a lack of specialized training, LLMs suffer at generating correct entity IDs. Furthermore, training an LLM to perform EL is cost-intensive. Building upon these insights, we introduce LLM-Augmented Entity Linking LLMAEL, a plug-and-play approach to enhance entity linking through LLM data augmentation. We leverage LLMs as knowledgeable context augmenters, generating mention-centered descriptions as additional input, while preserving traditional EL models for task specific processing. Experiments on 6 standard datasets show that the vanilla LLMAEL outperforms baseline EL models in most cases, while the fine-tuned LLMAEL set the new state-of-the-art results across all 6 benchmarks.

翻译：实体链接模型经过良好训练，能够根据给定上下文将提及映射到对应实体。然而，由于训练数据有限，实体链接模型在消歧长尾实体方面存在困难。与此同时，大型语言模型在解释非常见提及方面表现更为稳健。但由于缺乏专门训练，大型语言模型在生成正确实体ID方面存在不足。此外，训练大型语言模型执行实体链接任务成本高昂。基于这些发现，我们提出LLM增强实体链接方法LLMAEL，这是一种通过LLM数据增强提升实体链接性能的即插即用方案。我们利用大型语言模型作为知识丰富的上下文增强器，生成以提及为中心的描述作为附加输入，同时保留传统实体链接模型进行任务专用处理。在6个标准数据集上的实验表明，基础版LLMAEL在多数情况下优于基线实体链接模型，而微调版LLMAEL在所有6个基准测试中均取得了最新的最优结果。