OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting

TL;DR

OneNet is a novel framework that leverages large language models for few-shot entity linking without fine-tuning, using prompting-based components to improve accuracy and reduce hallucinations.

Contribution

It introduces a pioneering prompt-based approach for few-shot entity linking with LLMs, eliminating the need for fine-tuning and enhancing performance.

Findings

Outperforms state-of-the-art methods on seven benchmarks

Effective in few-shot scenarios with limited training data

Reduces hallucinations through a novel consensus algorithm

Abstract

Entity Linking (EL) is the process of associating ambiguous textual mentions to specific entities in a knowledge base. Traditional EL methods heavily rely on large datasets to enhance their performance, a dependency that becomes problematic in the context of few-shot entity linking, where only a limited number of examples are available for training. To address this challenge, we present OneNet, an innovative framework that utilizes the few-shot learning capabilities of Large Language Models (LLMs) without the need for fine-tuning. To the best of our knowledge, this marks a pioneering approach to applying LLMs to few-shot entity linking tasks. OneNet is structured around three key components prompted by LLMs: (1) an entity reduction processor that simplifies inputs by summarizing and filtering out irrelevant entities, (2) a dual-perspective entity linker that combines contextual cues and prior knowledge for precise entity linking, and (3) an entity consensus judger that employs a unique consistency algorithm to alleviate the hallucination in the entity linking reasoning. Comprehensive evaluations across seven benchmark datasets reveal that OneNet outperforms current state-of-the-art entity linking methods.