通过优化向量检索与指令设计，提升问答系统精度
Enhancing Question Answering Precision with Optimized Vector Retrieval and Instructions
- 采用小段落分块（100字无重叠）结合向量检索增强上下文
- 小段落分块在测试集上表现最佳，优于基于句子的语义分块
- 适合追求高效精准问答的开发者和研究者
问答（QA）是信息检索（IR）与语言模型的重要应用，当前趋势是使用带有嵌入参数的预训练大模型。然而，利用这些大语言模型（LLM）提升问答性能需要大量计算资源进行微调。本文提出一种新方法，通过整合优化的向量检索与指令策略来提升问答性能。该方法基于检索增强，包含文档嵌入、向量检索与上下文构建三个阶段。我们实验了多种文本分块策略与相似度函数组合，分析其对问答效果的影响。结果表明，采用100字无重叠的小段落分块的模型表现最佳，显著优于基于句子的语义分块模型。文中还讨论了典型问答案例，深入解析了两阶段框架如何提升模型性能。
原文摘要 · Abstract (English)
Question-answering (QA) is an important application of Information Retrieval (IR) and language models, and the latest trend is toward pre-trained large neural networks with embedding parameters. Augmenting QA performances with these LLMs requires intensive computational resources for fine-tuning. We propose an innovative approach to improve QA task performances by integrating optimized vector retrievals and instruction methodologies. Based on retrieval augmentation, the process involves document embedding, vector retrieval, and context construction for optimal QA results. We experiment with different combinations of text segmentation techniques and similarity functions, and analyze their impacts on QA performances. Results show that the model with a small chunk size of 100 without any overlap of the chunks achieves the best result and outperforms the models based on semantic segmentation using sentences. We discuss related QA examples and offer insight into how model performances are improved within the two-stage framework.
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。