LLMAEL：大型語言模型是實體鏈接的良好上下文增強器。

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

實體連結（EL）模型在根據給定上下文將提及映射到相應實體方面訓練有素。然而，由於訓練數據有限，EL 模型在消除長尾實體的歧義性方面遇到困難。與此同時，大型語言模型（LLMs）更能夠解釋不常見的提及。然而，由於缺乏專門的訓練，LLMs 在生成正確的實體 ID 方面遇到困難。此外，訓練 LLMS 來執行 EL 是成本高昂的。基於這些見解，我們介紹了 LLMAEL（LLM-Augmented Entity Linking），這是一種通過 LLMS 數據增強來增強實體連結的即插即用方法。我們利用 LLMS 作為知識上下文增強器，生成以提及為中心的描述作為附加輸入，同時保留傳統 EL 模型進行特定任務處理。對 6 個標準數據集的實驗表明，原始 LLMAEL 在大多數情況下優於基準 EL 模型，而微調 LLMAEL 在所有 6 個基準測試中設置了新的最先進結果。

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.