A human author can write any length of story without losing coherence. Also, they always bring the story to a proper ending, an ability that current language models lack. In this work, we present the LongStory for coherent, complete, and length-controlled long story generation. LongStory introduces two novel methodologies: (1) the long and short-term contexts weight calibrator (CWC) and (2) long story structural positions (LSP). The CWC adjusts weights for long-term context Memory and short-term context Cheating, acknowledging their distinct roles. The LSP employs discourse tokens to convey the structural positions of a long story. Trained on three datasets with varied average story lengths, LongStory outperforms other baselines, including the strong story generator Plotmachine, in coherence, completeness, relevance, and repetitiveness. We also perform zero-shot tests on each dataset to assess the model's ability to predict outcomes beyond its training data and validate our methodology by comparing its performance with variants of our model.

我们提出了LongStory，一种用于连贯、完整且受长度控制的长篇故事生成的方法。它引入了两种新方法：长期和短期上下文权重校准器（CWC）和长篇故事结构位置（LSP）。在多个数据集上训练，LongStory在连贯性、完整性、相关性和重复性方面优于其他基线，包括强大的故事生成器Plotmachine。我们还对每个数据集进行了零样本测试，评估该模型在超出其训练数据范围的情况下预测结果的能力，并通过与我们模型的变体进行比较来验证我们的方法。

LongStory: 连贯、完整且长度可控的长篇故事生成