论文标题
Corrpus：基于代码的结构化提示，以了解神经符号的故事理解
CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding
论文作者
论文摘要
故事的产生和理解 - 与所有NLG/NLU任务一样，已经看到了神经肯定工作的激增。研究人员已经认识到，尽管大型语言模型（LLMS）具有巨大的效用，但它们可以通过象征性手段来增强，以变得更好，并弥补神经网络可能存在的任何缺陷。但是，就创建它们所需的时间和专业知识而言，符号方法的成本非常高。在这项工作中，我们利用了诸如Codex之类的最先进的Code-llms，以引导使用符号方法来跟踪故事状态并有助于故事理解。我们表明，我们的Corrpus系统和抽象的提示程序可以使用最少的手工工程来击败当前的先前存在的故事理解任务（BABI任务2和RE^3）的最先进的结构化LLM技术。我们希望这项工作可以帮助强调符号表示的重要性，并为LLMS的专门提示，因为这些模型需要一些指导来正确执行推理任务。
Story generation and understanding -- as with all NLG/NLU tasks -- has seen a surge in neurosymbolic work. Researchers have recognized that, while large language models (LLMs) have tremendous utility, they can be augmented with symbolic means to be even better and to make up for any flaws that the neural networks might have. However, symbolic methods are extremely costly in terms of the amount of time and expertise needed to create them. In this work, we capitalize on state-of-the-art Code-LLMs, such as Codex, to bootstrap the use of symbolic methods for tracking the state of stories and aiding in story understanding. We show that our CoRRPUS system and abstracted prompting procedures can beat current state-of-the-art structured LLM techniques on pre-existing story understanding tasks (bAbI Task 2 and Re^3) with minimal hand engineering. We hope that this work can help highlight the importance of symbolic representations and specialized prompting for LLMs as these models require some guidance for performing reasoning tasks properly.
