KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
This addresses the issue of rigid schema and semantic ambiguity in KGQA for users needing more accurate and comprehensive question answering, representing a novel method rather than an incremental improvement.
The paper tackles the problem of low coverage in Knowledge Graph Question Answering (KGQA) by introducing KERAG, a Knowledge-Enhanced Retrieval-Augmented Generation pipeline that retrieves broader subgraphs to improve answer quality, resulting in a 7% improvement over state-of-the-art solutions and 10-21% over GPT-4o (Tool).
Retrieval-Augmented Generation (RAG) mitigates hallucination in Large Language Models (LLMs) by incorporating external data, with Knowledge Graphs (KGs) offering crucial information for question answering. Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing, which typically retrieves knowledge strictly necessary for answer generation, thus often suffer from low coverage due to rigid schema requirements and semantic ambiguity. We present KERAG, a novel KG-based RAG pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information. Our retrieval-filtering-summarization approach, combined with fine-tuned LLMs for Chain-of-Thought reasoning on knowledge sub-graphs, reduces noises and improves QA for both simple and complex questions. Experiments demonstrate that KERAG surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%.