用渐进式揭示本体，让大模型高效查询企业数据
Using off-the-shelf LLMs to query enterprise data by progressively revealing ontologies
- 通过逐步暴露所需本体片段，突破提示词长度限制
- 在不微调模型的前提下，显著提升自然语言转查询的准确率
- 适合需要对接复杂企业数据系统的开发者和工程师
本体可提升大语言模型将自然语言查询转换为SQL或SPARQL等形式化查询的准确性。现有方法有两种：一是微调模型以注入领域知识，二是零样本提示法，将本体作为输入的一部分。然而，现代企业通常拥有过大本体，无法完整放入提示词中（受LLM上下文长度限制）。本文提出一种渐进式揭示策略，仅在回答特定问题时动态加载‘足够’的本体内容，有效解决规模瓶颈问题。
原文摘要 · Abstract (English)
Ontologies are known to improve the accuracy of Large Language Models (LLMs) when translating natural language queries into a formal query language like SQL or SPARQL. There are two ways to leverage ontologies when working with LLMs. One is to fine-tune the model, i.e., to enhance it with specific domain knowledge. Another is the zero-shot prompting approach, where the ontology is provided as part of the input question. Unfortunately, modern enterprises typically have ontologies that are too large to fit in a prompt due to LLM's token size limitations. We present a solution that incrementally reveals "just enough" of an ontology that is needed to answer a given question.
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。