CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph

TL;DR

CogMG is a collaborative framework that uses knowledge graphs to improve large language models' factual accuracy and reduce hallucinations in question-answering tasks by identifying and enriching missing knowledge triples.

Contribution

This work introduces CogMG, a novel collaborative augmentation framework that leverages knowledge graphs to address LLM hallucinations and knowledge update misalignment in QA applications.

Findings

Significant reduction in hallucinations in QA responses.

Enhanced factual accuracy through knowledge graph augmentation.

Effective integration of knowledge graphs with LLMs demonstrated.

Abstract

Large language models have become integral to question-answering applications despite their propensity for generating hallucinations and factually inaccurate content. Querying knowledge graphs to reduce hallucinations in LLM meets the challenge of incomplete knowledge coverage in knowledge graphs. On the other hand, updating knowledge graphs by information extraction and knowledge graph completion faces the knowledge update misalignment issue. In this work, we introduce a collaborative augmentation framework, CogMG, leveraging knowledge graphs to address the limitations of LLMs in QA scenarios, explicitly targeting the problems of incomplete knowledge coverage and knowledge update misalignment. The LLMs identify and decompose required knowledge triples that are not present in the KG, enriching them and aligning updates with real-world demands. We demonstrate the efficacy of this approach through a supervised fine-tuned LLM within an agent framework, showing significant improvements in reducing hallucinations and enhancing factual accuracy in QA responses. Our code and video are publicly available.