让AI生成内容时可调事实准确性和信息量，满足不同需求。
Factuality on Demand: Controlling the Factuality-Informativeness Trade-off in Text Generation
- 通过用户指定事实约束条件控制生成内容
- 合成数据训练使模型同时保持高准确性和高信息量
- 适合需要平衡真实与丰富性的问答、摘要场景
大型语言模型在回应查询时面临事实性与信息量的固有权衡：可生成低信息但高准确的内容，或高信息但可能不准确的内容。不同应用场景对二者比例需求不同。本文提出事实可控生成（FCG）框架，允许用户在查询中附加事实性约束。评估采用两个维度：是否遵守事实约束、输出信息量。通过合成数据训练模型，结果表明该方法显著提升模型在遵循事实要求的同时维持输出信息量的能力。
原文摘要 · Abstract (English)
Large language models (LLMs) encode knowledge with varying degrees of confidence. When responding to queries, models face an inherent trade-off: they can generate responses that are less informative but highly factual, or more informative but potentially less accurate. Different applications demand different balances between informativeness and factuality. We introduce Factuality-Controlled Generation (FCG), a framework that enables users to specify factuality constraints alongside their queries. We propose to evaluate FCG performance on two dimensions: adherence to factuality constraints and response informativeness. We propose to train models on the FCG task using synthetic data, and show that our synthetic training significantly improves models' ability to both respect factuality requirements and maintain informativeness in their outputs.
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。