arXiv 2507.124252025-07-16cs.CLcs.AIcs.CEcs.IR

推进面向结构化企业数据与内部数据的检索增强生成

Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data

IIT Roorkee（罗尔基大学）

Chandana Cheerla

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对LLM处理企业结构化数据的局限，提出结合稠密嵌入与BM25混合检索、语义分块及交叉编码器重排序的先进RAG框架，显著提升了企业数据检索的准确率与响应质量。

摘要：

各组织日益依赖包括HR记录、结构化报告和表格文档在内的专有企业数据进行关键决策。尽管大型语言模型（LLMs）具备强大的生成能力，但受限于静态预训练、短上下文窗口以及处理异构数据格式的挑战。传统的检索增强生成（RAG）框架弥补了部分缺陷，但在处理结构化和半结构化数据时仍常显不足。本工作提出了一种先进的RAG框架，结合使用稠密嵌入（all-mpnet-base-v2）和BM25的混合检索策略，并通过SpaCy NER的元数据感知过滤和交叉编码器重排序进行增强。该框架应用语义分块以保持文本连贯性，并保留表格数据结构以维护行列完整性。量化索引优化了检索效率，而人在回路反馈和对话记忆则提升了适应性。在企业数据集上的实验显示出显著提升：Precision@5提高了15%（90对比75），Recall@5提高了13%（87对比74），平均倒数排名提高了16%（0.85对比0.69）。在5点Likert量表上的定性评估显示，忠实度（4.6对比3.0）、完整性（4.2对比2.5）和相关性（4.5对比3.2）得分更高。这些结果证明了该框架在企业任务中提供准确、全面且上下文相关响应的有效性。未来工作包括扩展至多模态数据及集成基于智能体的检索。源代码将发布于https://github.com/CheerlaChandana/Enterprise-Chatbot

英文摘要：

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

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

AI总结：

摘要：

英文摘要：

相关论文