When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured that this can teach the model the behavior of hallucinating factually incorrect responses, as the model is trained to generate facts that are not grounded in its pre-existing knowledge. In this work, we study the impact of such exposure to new knowledge on the capability of the fine-tuned model to utilize its pre-existing knowledge. To this end, we design a controlled setup, focused on closed-book QA, where we vary the proportion of the fine-tuning examples that introduce new knowledge. We demonstrate that large language models struggle to acquire new factual knowledge through fine-tuning, as fine-tuning examples that introduce new knowledge are learned significantly slower than those consistent with the model's knowledge. However, we also find that as the examples with new knowledge are eventually learned, they linearly increase the model's tendency to hallucinate. Taken together, our results highlight the risk in introducing new factual knowledge through fine-tuning, and support the view that large language models mostly acquire factual knowledge through pre-training, whereas fine-tuning teaches them to use it more efficiently.

翻译：当通过监督微调对齐大型语言模型时，它们可能接触到预训练阶段未获取的新事实信息。通常推测，这可能导致模型产生事实上不正确的幻觉行为，因为模型被训练生成并非基于其已有知识的答案。本研究探讨了接触新知识对微调模型利用已有知识能力的影响。为此，我们设计了一个受控实验环境（聚焦于闭卷问答任务），通过改变引入新知识的微调样本比例进行分析。实验表明，大型语言模型难以通过微调获取新的事实知识——引入新知识的微调样本学习速度显著慢于与模型已有知识一致的样本。然而，我们也发现当新知识样本最终被学习后，会线性增加模型产生幻觉的倾向。综合而言，我们的结果凸显了通过微调引入新事实知识的风险，并支持以下观点：大型语言模型主要通过预训练获取事实知识，而微调的作用是使其更高效地运用这些知识。