按需事实性：在文本生成中控制事实性与信息性之间的权衡
Factuality on Demand: Controlling the Factuality-Informativeness Trade-off in Text Generation
AI总结：
本文提出Factuality-Controlled Generation框架，通过合成数据训练提升模型在信息性与事实性之间的平衡能力。
摘要：
大型语言模型（LLMs）在不同程度上编码知识。在响应查询时，模型面临固有的权衡：它们可以生成信息较少但事实性较高的响应，或信息更多但可能准确性较低的响应。不同的应用需求不同的信息性与事实性之间的平衡。我们引入了事实性受控生成（FCG），这是一个框架，使用户能够在查询中指定事实性约束。我们提出在两个维度上评估FCG的性能：对事实性约束的遵守程度和响应的信息性。我们提出使用合成数据训练模型在FCG任务上，并展示我们的合成训练显著提高了模型在输出中尊重事实性要求和保持信息性的能力。
英文摘要：
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.
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。
