用知识图谱增强检索生成，让企业聊天机器人读懂私有文档。
From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants
- 构建低噪声知识图谱，通过种子实体增量消歧与置信度过滤。
- 相比现有系统，无关回答减少50%以上，完全相关回答提升88%。
- 适合需要安全访问内部文档的企业级对话系统开发者。
Adobe Experience Platform AI Assistant 是一个对话式工具，使组织能够通过聊天机器人无缝访问专有的企业数据。然而，由于访问限制，大语言模型（LLMs）无法检索这些内部文档，从而限制了其生成准确零样本回答的能力。为克服这一局限，我们采用由知识图谱（KG）驱动的检索增强生成（RAG）框架，从外部知识源检索相关信息，使 LLM 能够回答关于私有或此前未见过的文档集合的问题。本文提出一种构建高质量、低噪声知识图谱的新方法，应用多种技术，包括基于种子概念的增量实体消歧、基于相似性的去重过滤、为实体-关系对分配置信度以筛选高置信度对，并将事实链接到源文档以保证可追溯性。KG-RAG 系统检索出的相关三元组被添加到用户提示上下文，再送入 LLM 生成响应。评估结果表明，该方法显著提升了回答相关性，相比现有生产系统，无关回答减少超过50%，完全相关回答增加88%。
原文摘要 · Abstract (English)
The Adobe Experience Platform AI Assistant is a conversational tool that enables organizations to interact seamlessly with proprietary enterprise data through a chatbot. However, due to access restrictions, Large Language Models (LLMs) cannot retrieve these internal documents, limiting their ability to generate accurate zero-shot responses. To overcome this limitation, we use a Retrieval-Augmented Generation (RAG) framework powered by a Knowledge Graph (KG) to retrieve relevant information from external knowledge sources, enabling LLMs to answer questions over private or previously unseen document collections. In this paper, we propose a novel approach for building a high-quality, low-noise KG. We apply several techniques, including incremental entity resolution using seed concepts, similarity-based filtering to deduplicate entries, assigning confidence scores to entity-relation pairs to filter for high-confidence pairs, and linking facts to source documents for provenance. Our KG-RAG system retrieves relevant tuples, which are added to the user prompts context before being sent to the LLM generating the response. Our evaluation demonstrates that this approach significantly enhances response relevance, reducing irrelevant answers by over 50% and increasing fully relevant answers by 88% compared to the existing production system.
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。