让大模型查权威数据，回答更准确。
Knowing When to Ask -- Bridging Large Language Models and Data
- 训练模型自动生成查询语句，从公开数据仓库取数。
- 结合真实统计数据后，回答错误率降低近一半。
- 适合需要可靠事实的科研、政策与数据分析场景。
大型语言模型在回答涉及数值和统计信息的问题时容易生成错误内容。本文提出一种方法，通过将大模型与 Data Commons（一个来自联合国、疾控中心及全球人口普查机构等可信组织的开源公共统计数据仓库）集成，提升其准确性。研究探索两种主要方法：检索交织生成（RIG），即训练模型生成自然语言查询以从 Data Commons 中检索数据；以及检索增强生成（RAG），即获取相关数据表并作为上下文注入提示中。在多样化查询任务上的评估表明，该方法显著提升了模型输出的事实准确性。本工作为构建基于可验证统计数据、具备复杂事实推理能力的可信大模型迈出关键一步。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are prone to generating factually incorrect information when responding to queries that involve numerical and statistical data or other timely facts. In this paper, we present an approach for enhancing the accuracy of LLMs by integrating them with Data Commons, a vast, open-source repository of public statistics from trusted organizations like the United Nations (UN), Center for Disease Control and Prevention (CDC) and global census bureaus. We explore two primary methods: Retrieval Interleaved Generation (RIG), where the LLM is trained to produce natural language queries to retrieve data from Data Commons, and Retrieval Augmented Generation (RAG), where relevant data tables are fetched from Data Commons and used to augment the LLM's prompt. We evaluate these methods on a diverse set of queries, demonstrating their effectiveness in improving the factual accuracy of LLM outputs. Our work represents an early step towards building more trustworthy and reliable LLMs that are grounded in verifiable statistical data and capable of complex factual reasoning.
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。