CoRRPUS:基于代码的结构化提示用于神经符号故事理解
CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding
AI总结:
本文提出CoRRPUS系统,利用Codex等代码大语言模型引导符号方法跟踪故事状态,在bAbI Task 2和Re^3任务上以极少手工工程超越现有结构化LLM技术,强调符号表示与专门化提示对推理的重要性。
摘要:
故事生成与理解——如同所有自然语言生成/自然语言理解任务一样——见证了神经符号研究的激增。研究人员已经认识到,尽管大语言模型(LLMs)具有巨大的实用性,但可以通过符号手段对其进行增强,使其表现更佳,并弥补神经网络可能存在的缺陷。然而,符号方法在创建所需的时间和专业知识方面成本极高。在这项工作中,我们利用最先进的代码大语言模型(Code-LLMs),如Codex,来引导符号方法的使用,以跟踪故事状态并辅助故事理解。我们展示了我们的CoRRPUS系统和抽象化提示流程能够在已有的故事理解任务(bAbI Task 2和Re^3)上以极少的手工工程击败当前最先进的结构化LLM技术。我们希望这项工作能够帮助强调符号表示和专门化提示对LLMs的重要性,因为这些模型在执行推理任务时需要一定的引导才能正确完成。
英文摘要:
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.
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。