While large language models are able to retain vast amounts of world knowledge seen during pretraining, such knowledge is prone to going out of date and is nontrivial to update. Furthermore, these models are often used under temporal misalignment, tasked with answering questions about the present, despite having only been trained on data collected in the past. To mitigate the effects of temporal misalignment, we propose fact duration prediction: the task of predicting how long a given fact will remain true. In our experiments, we demonstrate that identifying which facts are prone to rapid change can help models avoid reciting outdated information and determine which predictions require seeking out up-to-date knowledge sources. We also show how modeling fact duration improves calibration for knowledge-intensive tasks, such as open-retrieval question answering, under temporal misalignment, by discarding volatile facts. Our data and code are released publicly at https://github.com/mikejqzhang/mitigating_misalignment.

翻译：虽然大型语言模型能够保留预训练阶段接触的大量世界知识，但这些知识容易过时且难以更新。此外，这些模型常在时间错位场景下使用——尽管仅基于过去收集的数据训练，却被要求回答当前问题。为缓解时间错位的影响，我们提出事实持续时间预测任务：预测给定事实将持续有效多久。实验表明，识别哪些事实易快速变化，有助于模型避免复述过时信息，并决定哪些预测需要检索最新知识源。我们还展示了如何通过建模事实持续时间，在时间错位条件下丢弃易变事实，从而提升开放检索问答等知识密集型任务的校准性能。相关数据与代码已在 https://github.com/mikejqzhang/mitigating_misalignment 公开。