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

2025-05-26

AI Summary

Large language models (LLMs) frequently generate hallucinations when lacking domain knowledge, and existing knowledge graph (KG)-enhanced reasoning methods often yield incomplete or factually inconsistent inference paths. To address this, we propose the Self-Reflective Planning (SRP) framework—the first to introduce a closed-loop “retrieve-judge-edit” paradigm for KG-augmented reasoning. SRP retrieves structured evidence from KGs, performs iterative path planning guided by reference answers, and dynamically corrects factual errors within generated reasoning paths. The framework integrates LLMs, KG retrieval, reference-guided planning, iterative self-reflection, and path editing. Evaluated on three public benchmark datasets, SRP significantly outperforms strong baselines, achieving substantial improvements in both answer accuracy and factual consistency of inference paths. These results demonstrate SRP’s capacity for high-reliability, verifiable question answering.

Technology Category

• Knowledge Representation and Reasoning: Reasoning with Beliefs
• Planning, Routing, and Scheduling: Planning with Language Models
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Reducing LLM hallucinations in reasoning tasks
• Improving reasoning path completeness with KGs
• Enhancing answer reliability through iterative reflection

Innovation

• Integrates LLMs with knowledge graphs iteratively
• Uses reference-guided reasoning for path generation
• Implements iterative reflection for reliable retrieval