Classic4Children：利用大语言模型将中国文学经典改编为儿童读物
Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model
AI总结：
本文提出InstructChild方法，通过指令微调、可读性奖励对齐和前瞻解码，使大语言模型能够将中国文学经典改编为符合儿童阅读偏好的文本，并构建Classic4Children数据集验证其有效性。
摘要：
中国文学经典具有重要的文化和教育价值，在道德、历史和人性方面提供了深刻的洞见。这些作品往往包含文言文和复杂的叙事，使儿童难以阅读。为了弥合这一差距，我们引入了一项面向儿童的文学改编（CLA）任务，旨在将中国文学经典改编为适合儿童阅读的、引人入胜且易于理解的文本。然而，近期的大语言模型（LLMs）忽视了儿童的阅读偏好（即生动的人物刻画、简洁的叙事结构和适当的可读性），这给CLA任务带来了挑战。在本文中，我们提出了一种名为InstructChild的方法，通过将这些偏好注入大语言模型来完成改编。具体来说，我们首先获取人物性格和叙事结构作为额外信息，用于细粒度指令微调。然后，我们设计了一种可读性指标作为奖励，使大语言模型与儿童的阅读水平对齐。最后，在推理过程中采用前瞻解码策略来提高生成文本的可读性。为了支持CLA任务的评估，我们构建了Classic4Children数据集，该数据集包含中国文学四大名著的原文版本和儿童友好版本。实验结果表明，我们的InstructChild方法显著提升了自动评估和人工评估的性能。
英文摘要：
Chinese literary classics hold significant cultural and educational value, offering deep insights into morality, history, and human nature. These works often include classical Chinese and complex narratives, making them difficult for children to read. To bridge this gap, we introduce a child-friendly literary adaptation (CLA) task to adapt the Chinese literary classic into engaging and accessible text for children. However, recent large language models (LLMs) overlook children's reading preferences (\ie, vivid character portrayals, concise narrative structures, and appropriate readability), which poses challenges in CLA. In this paper, we propose a method called InstructChild, which augments the LLM with these preferences for adaptation. Specifically, we first obtain the characters' personalities and narrative structure as additional information for fine-grained instruction tuning. Then, we devise a readability metric as the reward to align the LLM with the children's reading level. Finally, a lookahead decoding strategy is applied to improve the readability of the generated text during inference. To support the evaluation of CLA task, we construct the Classic4Children dataset, which comprises both the original and child-friendly versions of the Four Great Classical Novels of Chinese literature. Experimental results show that our InstructChild significantly improves automatic and human evaluation performance.
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。
