Knowledge Bases in Support of Large Language Models for Processing Web News

TL;DR

This paper presents a framework combining rule-based extraction and graph convolution to enhance large language models' ability to process web news by building specialized knowledge bases for improved classification.

Contribution

It introduces a novel framework that integrates explicit knowledge extraction with implicit LLM knowledge for better news processing and classification.

Findings

Effective news category classification demonstrated

Framework outperforms baseline models

Promising results on multiple datasets

Abstract

Large Language Models (LLMs) have received considerable interest in wide applications lately. During pre-training via massive datasets, such a model implicitly memorizes the factual knowledge of trained datasets in its hidden parameters. However, knowledge held implicitly in parameters often makes its use by downstream applications ineffective due to the lack of common-sense reasoning. In this article, we introduce a general framework that permits to build knowledge bases with an aid of LLMs, tailored for processing Web news. The framework applies a rule-based News Information Extractor (NewsIE) to news items for extracting their relational tuples, referred to as knowledge bases, which are then graph-convoluted with the implicit knowledge facts of news items obtained by LLMs, for their classification. It involves two lightweight components: 1) NewsIE: for extracting the structural information of every news item, in the form of relational tuples; 2) BERTGraph: for graph convoluting the implicit knowledge facts with relational tuples extracted by NewsIE. We have evaluated our framework under different news-related datasets for news category classification, with promising experimental results.