Retrieval-Augmented Generation (RAG) systems using large language models (LLMs) often generate inaccurate responses due to the retrieval of irrelevant or loosely related information. Existing methods, which operate at the document level, fail to effectively filter out such content. We propose LLM-driven chunk filtering, ChunkRAG, a framework that enhances RAG systems by evaluating and filtering retrieved information at the chunk level. Our approach employs semantic chunking to divide documents into coherent sections and utilizes LLM-based relevance scoring to assess each chunk's alignment with the user's query. By filtering out less pertinent chunks before the generation phase, we significantly reduce hallucinations and improve factual accuracy. Experiments show that our method outperforms existing RAG models, achieving higher accuracy on tasks requiring precise information retrieval. This advancement enhances the reliability of RAG systems, making them particularly beneficial for applications like fact-checking and multi-hop reasoning.

翻译：基于大语言模型（LLM）的检索增强生成（RAG）系统常因检索到不相关或弱相关信息而生成错误回答。现有方法在文档层面进行操作，难以有效过滤此类内容。我们提出一种LLM驱动的分块过滤框架ChunkRAG，通过在分块层面对检索信息进行评估与过滤来增强RAG系统。该方法采用语义分块技术将文档划分为连贯的段落，并利用基于LLM的相关性评分机制评估每个分块与用户查询的匹配度。通过在生成阶段前过滤低关联分块，我们显著减少了幻觉现象并提升了事实准确性。实验表明，本方法在需要精确信息检索的任务上优于现有RAG模型，实现了更高的准确率。这一进展增强了RAG系统的可靠性，使其在事实核查与多跳推理等应用中具有显著优势。