LLMAEL：大型语言模型是实体链接的良好上下文增强器

LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking

July 4, 2024

作者: Amy Xin, Yunjia Qi, Zijun Yao, Fangwei Zhu, Kaisheng Zeng, Xu Bin, Lei Hou, Juanzi Li

cs.AI

摘要

实体链接（EL）模型在根据给定上下文将提及映射到相应实体方面经过良好训练。然而，由于训练数据有限，EL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（LLMs）更擅长解释不常见的提及。然而，由于缺乏专门训练，LLMs在生成正确实体ID方面存在困难。此外，训练LLM执行EL是成本高昂的。基于这些见解，我们引入了LLM增强实体链接（LLMAEL），这是一种通过LLM数据增强来增强实体链接的即插即用方法。我们利用LLMs作为知识上下文增强器，生成以提及为中心的描述作为额外输入，同时保留传统EL模型进行特定任务处理。对6个标准数据集的实验表明，原始LLMAEL在大多数情况下优于基线EL模型，而经过微调的LLMAEL在所有6个基准测试中取得了新的最先进结果。

English

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.