Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction

TL;DR

This paper introduces a collaborative framework combining large language models with small neural models to improve the accuracy of relational triple extraction from complex sentences, enhancing knowledge extraction tasks.

Contribution

It proposes an evaluation-filtering framework with a novel neural evaluation model that boosts large language models' performance in extracting triples from complex sentences.

Findings

Enhanced extraction accuracy for complex sentences.

Effective integration of small models with large language models.

Improved precision in relational triple extraction tasks.

Abstract

Relation triple extraction, which outputs a set of triples from long sentences, plays a vital role in knowledge acquisition. Large language models can accurately extract triples from simple sentences through few-shot learning or fine-tuning when given appropriate instructions. However, they often miss out when extracting from complex sentences. In this paper, we design an evaluation-filtering framework that integrates large language models with small models for relational triple extraction tasks. The framework includes an evaluation model that can extract related entity pairs with high precision. We propose a simple labeling principle and a deep neural network to build the model, embedding the outputs as prompts into the extraction process of the large model. We conduct extensive experiments to demonstrate that the proposed method can assist large language models in obtaining more accurate extraction results, especially from complex sentences containing multiple relational triples. Our evaluation model can also be embedded into traditional extraction models to enhance their extraction precision from complex sentences.