The integration of Knowledge Graphs (KGs) and Large Language Models (LLMs) is emerging as a transformative advancement in AI, particularly within Question Answering (QA) systems. Traditional QA systems, constrained by static knowledge bases, have struggled with multimodal queries and personalized responses. The deep integration of KGs and LLMs offers a novel approach, combining the structured, contextual understanding of KGs with the semantic parsing capabilities of LLMs. This review explores the methodologies, algorithms, datasets, and applications of KG-LLM integration in QA systems, highlighting key research that enhances model performance, reasoning, and domain-specific applications. It addresses technical challenges such as data consistency, semantic understanding, and system optimization. Future directions focus on improving intrinsic model performance and achieving deeper integration of KGs and LLMs. This comprehensive overview underscores the potential of KG-LLM synergy to significantly improve service quality across diverse industries, including education and healthcare.