用自动生成的问题编码知识，提升文档检索效果且无需微调
Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning
- 用生成的问题覆盖词法和语义空间，形成精准检索线索
- 单跳检索召回率达0.84，比传统切块方法高60%
- 无需微调，存储量减少80%，适合快速部署的问答系统
本研究提出一种基于问题的知识编码方法，无需微调或传统文本切块即可提升检索增强生成（RAG）系统性能。通过生成覆盖词汇与语义空间的问题来编码文本内容，并结合定制的语法重排序策略，实现精准检索。在109篇科学论文的单跳检索中，召回率@3达0.84，较传统切块方法提升60%。引入‘paper-cards’（每篇不超过300字符的摘要），使BM25检索在简化技术查询下的MRR@3从0.56升至0.85。在多跳任务中，该方法在LongBench 2WikiMultihopQA数据集上以LLaMA2-Chat-7B获得F1=0.52，优于切块法（0.328）与微调基线（0.412）。该方法避免微调、降低延迟、减少向量存储需求80%，具备可扩展性与高效性。
原文摘要 · Abstract (English)
This study presents a question-based knowledge encoding approach that improves retrieval-augmented generation (RAG) systems without requiring fine-tuning or traditional chunking. We encode textual content using generated questions that span the lexical and semantic space, creating targeted retrieval cues combined with a custom syntactic reranking method. In single-hop retrieval over 109 scientific papers, our approach achieves a Recall@3 of 0.84, outperforming traditional chunking methods by 60 percent. We also introduce "paper-cards", concise paper summaries under 300 characters, which enhance BM25 retrieval, increasing MRR@3 from 0.56 to 0.85 on simplified technical queries. For multihop tasks, our reranking method reaches an F1 score of 0.52 with LLaMA2-Chat-7B on the LongBench 2WikiMultihopQA dataset, surpassing chunking and fine-tuned baselines which score 0.328 and 0.412 respectively. This method eliminates fine-tuning requirements, reduces retrieval latency, enables intuitive question-driven knowledge access, and decreases vector storage demands by 80%, positioning it as a scalable and efficient RAG alternative.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。