Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving
This work addresses the challenge of unreliable outputs in LLMs for complex problem-solving, offering a domain-specific improvement in KGQA.
The paper tackles the problem of LLMs struggling with knowledge integration and complex reasoning in tasks like Knowledge Graph Question Answering by proposing CogGRAG, a cognition-inspired graph-based RAG framework, which outperforms baselines on four benchmark datasets with three LLM backbones.
Large language models (LLMs) have demonstrated transformative potential across various domains, yet they face significant challenges in knowledge integration and complex problem reasoning, often leading to hallucinations and unreliable outputs. Retrieval-Augmented Generation (RAG) has emerged as a promising solution to enhance LLMs accuracy by incorporating external knowledge. However, traditional RAG systems struggle with processing complex relational information and multi-step reasoning, limiting their effectiveness in advanced problem-solving tasks. To address these limitations, we propose CogGRAG, a cognition inspired graph-based RAG framework, designed to improve LLMs performance in Knowledge Graph Question Answering (KGQA). Inspired by the human cognitive process of decomposing complex problems and performing self-verification, our framework introduces a three-stage methodology: decomposition, retrieval, and reasoning with self-verification. By integrating these components, CogGRAG enhances the accuracy of LLMs in complex problem solving. We conduct systematic experiments with three LLM backbones on four benchmark datasets, where CogGRAG outperforms the baselines.