Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering

TL;DR

This paper introduces Self-Reflective Planning (SRP), a novel framework that combines large language models with knowledge graphs through iterative reasoning and reflection, significantly improving the reliability of question answering.

Contribution

The paper presents SRP, a new method that enhances LLM reasoning by iterative planning and reflection guided by knowledge graphs, reducing hallucinations and increasing factual accuracy.

Findings

SRP outperforms strong baselines on three datasets.

SRP demonstrates improved reasoning reliability.

Iterative reflection refines reasoning paths effectively.

Abstract

Recently, large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, yet they remain prone to hallucinations when reasoning with insufficient internal knowledge. While integrating LLMs with knowledge graphs (KGs) provides access to structured, verifiable information, existing approaches often generate incomplete or factually inconsistent reasoning paths. To this end, we propose Self-Reflective Planning (SRP), a framework that synergizes LLMs with KGs through iterative, reference-guided reasoning. Specifically, given a question and topic entities, SRP first searches for references to guide planning and reflection. In the planning process, it checks initial relations and generates a reasoning path. After retrieving knowledge from KGs through a reasoning path, it implements iterative reflection by judging the retrieval result and editing the reasoning path until the answer is correctly retrieved. Extensive experiments on three public datasets demonstrate that SRP surpasses various strong baselines and further underscore its reliable reasoning ability.