Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation

TL;DR

This paper analyzes failure points in retrieval-augmented generation systems using knowledge graphs, identifies key issues, and proposes Mindful-RAG, a framework that improves answer accuracy by focusing on intent and relevant context.

Contribution

It identifies eight critical failure points in KG-based RAG systems and introduces Mindful-RAG, a novel framework that enhances retrieval relevance and answer correctness.

Findings

Error patterns mainly stem from misunderstanding question intent.

Mindful-RAG improves answer relevance and correctness.

Framework explicitly targets identified failure points.

Abstract

Large Language Models (LLMs) are proficient at generating coherent and contextually relevant text but face challenges when addressing knowledge-intensive queries in domain-specific and factual question-answering tasks. Retrieval-augmented generation (RAG) systems mitigate this by incorporating external knowledge sources, such as structured knowledge graphs (KGs). However, LLMs often struggle to produce accurate answers despite access to KG-extracted information containing necessary facts. Our study investigates this dilemma by analyzing error patterns in existing KG-based RAG methods and identifying eight critical failure points. We observed that these errors predominantly occur due to insufficient focus on discerning the question's intent and adequately gathering relevant context from the knowledge graph facts. Drawing on this analysis, we propose the Mindful-RAG approach, a framework designed for intent-based and contextually aligned knowledge retrieval. This method explicitly targets the identified failures and offers improvements in the correctness and relevance of responses provided by LLMs, representing a significant step forward from existing methods.