提升企业数据问答准确率，专治表格和半结构化数据难处理问题
Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data
- 融合稠密向量与关键词检索，用命名实体识别过滤元数据并重排序
- 在企业数据集上召回率提升13%，精确率提高15%，排名分数上升16%
- 适合需要精准处理内部表格、报告的智能客服或决策系统
组织日益依赖专有的企业数据（如人力资源记录、结构化报告和表格文档）进行关键决策。尽管大语言模型具备强大生成能力，但受限于静态预训练、短上下文窗口及异构数据格式处理难题。传统检索增强生成框架虽部分弥补这些缺陷，却难以有效处理结构化与半结构化数据。本文提出一种先进RAG框架，结合密集嵌入（all-mpnet-base-v2）与BM25的混合检索策略，通过SpaCy NER实现元数据感知过滤，并采用交叉编码器重排序。框架采用语义分块保持文本连贯性，同时保留表格行列结构以确保完整性。量化索引优化检索效率，引入人机反馈与对话记忆提升适应性。在企业数据集上的实验显示：Precision@5提升15%（90→75），Recall@5提升13%（87→74），平均倒数排名提升16%（0.85→0.69）。定性评估表明，在忠实度（4.6→3.0）、完整度（4.2→2.5）和相关性（4.5→3.2）上均显著优于基线。结果证明该框架能为企事业单位任务提供准确、全面且上下文相关的回答。未来工作将拓展至多模态数据与基于代理的检索。源码将在https://github.com/CheerlaChandana/Enterprise-Chatbot发布。
原文摘要 · Abstract (English)
Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are limited by static pretraining, short context windows, and challenges in processing heterogeneous data formats. Conventional Retrieval-Augmented Generation (RAG) frameworks address some of these gaps but often struggle with structured and semi-structured data. This work proposes an advanced RAG framework that combines hybrid retrieval strategies using dense embeddings (all-mpnet-base-v2) and BM25, enhanced by metadata-aware filtering with SpaCy NER and cross-encoder reranking. The framework applies semantic chunking to maintain textual coherence and retains tabular data structures to preserve row-column integrity. Quantized indexing optimizes retrieval efficiency, while human-in-the-loop feedback and conversation memory improve adaptability. Experiments on enterprise datasets show notable improvements: Precision@5 increased by 15 percent (90 versus 75), Recall@5 by 13 percent (87 versus 74), and Mean Reciprocal Rank by 16 percent (0.85 versus 0.69). Qualitative evaluations show higher scores in Faithfulness (4.6 versus 3.0), Completeness (4.2 versus 2.5), and Relevance (4.5 versus 3.2) on a 5-point Likert scale. These results demonstrate the framework's effectiveness in delivering accurate, comprehensive, and contextually relevant responses for enterprise tasks. Future work includes extending to multimodal data and integrating agent-based retrieval. The source code will be released at https://github.com/CheerlaChandana/Enterprise-Chatbot
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。