训练数据如何塑造语言模型中参数知识和上下文知识的使用
How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
AI总结：
研究通过合成语料库实验，发现语言模型在处理参数知识和上下文知识时，需同时存在文档内重复、适度不一致和知识分布偏斜等特性才能实现稳健平衡的使用。
摘要：
大型语言模型同时利用预训练获得的参数知识和推理时提供的上下文知识。当这些来源冲突时，模型根据内部置信度进行仲裁，优先使用参数知识处理高置信度事实，而对不熟悉的事实则依赖上下文。然而，导致这些基本行为的训练条件仍不明确。本文通过受控实验使用合成语料库，识别出具体的数据特性，发现稳健平衡使用两种知识来源是三种通常被认为不利因素的共同作用结果，包括（i）文档内重复，（ii）适度的文档内不一致，以及（iii）知识分布偏斜。我们进一步展示了这些动态在真实世界语言模型预训练中的表现，并分析了训练后过程如何重塑仲裁策略。这些发现为设计支持语言模型可靠整合参数和上下文知识的训练数据提供了实证指导。
英文摘要：
Large language models leverage both parametric knowledge acquired during pretraining and in-context knowledge provided at inference time. Crucially, when these sources conflict, models arbitrate based on their internal confidence, preferring parametric knowledge for high-confidence facts while deferring to context for less familiar ones. However, the training conditions that give rise to these fundamental behaviors remain unclear. Here we conduct controlled experiments using synthetic corpora to identify the specific data properties that shape knowledge utilization. Our results reveal a counterintuitive finding: the robust, balanced use of both knowledge sources is an emergent property that requires the co-occurrence of three factors typically considered detrimental, including (i) intra-document repetition, (ii) a moderate degree of intra-document inconsistency, and (iii) a skewed knowledge distribution. We further show that these dynamics arise in real-world language model pretraining and analyze how post-training procedures reshape arbitration strategies. Together, our findings provide empirical guidance for designing training data that supports the reliable integration of parametric and in-context knowledge in language models.
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。
