arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.07699cs.AIcs.CLcs.SC
收藏

利用大型语言模型生成回答集程序

Leveraging Large Language Models to Generate Answer Set Programs

Arizona State University(亚利桑那州立大学);Samsung Research(三星研究院)

Adam Ishay, Zhun Yang, Joohyung Lee

AI总结:

本文提出结合 LLM 与 answer set programming 的神经符号方法,通过精心设计的逐步提示和少量示例,将逻辑谜题自然语言描述生成回答集程序,且错误多易于人工修正。

摘要:

大型语言模型(LLM),例如 GPT-3 和 GPT-4,已经在各种自然语言处理任务中表现出卓越性能,并显示出解决某些推理问题的能力。然而,尽管应用了各种提示技术,它们的推理能力仍然有限且相对浅显。相比之下,形式逻辑擅长处理复杂推理,但将自然语言描述转换为形式逻辑是一项具有挑战性的任务,非专家往往难以完成。本文提出一种神经符号方法,将大型语言模型与回答集编程(answer set programming)的优势结合起来。具体而言,我们使用 LLM 将逻辑谜题的自然语言描述转换为回答集程序。我们精心设计提示,使 LLM 能够以逐步方式把自然语言描述转换为回答集程序。令人惊讶的是,仅需少量上下文学习示例,LLM 就能生成具有相当复杂度的回答集程序。所产生的大多数错误都相对简单,人类可以轻松纠正,因此 LLM 能够有效辅助回答集程序的创建。

英文摘要:

Large language models (LLMs), such as GPT-3 and GPT-4, have demonstrated exceptional performance in various natural language processing tasks and have shown the ability to solve certain reasoning problems. However, their reasoning capabilities are limited and relatively shallow, despite the application of various prompting techniques. In contrast, formal logic is adept at handling complex reasoning, but translating natural language descriptions into formal logic is a challenging task that non-experts struggle with. This paper proposes a neuro-symbolic method that combines the strengths of large language models and answer set programming. Specifically, we employ an LLM to transform natural language descriptions of logic puzzles into answer set programs. We carefully design prompts for an LLM to convert natural language descriptions into answer set programs in a step by step manner. Surprisingly, with just a few in-context learning examples, LLMs can generate reasonably complex answer set programs. The majority of errors made are relatively simple and can be easily corrected by humans, thus enabling LLMs to effectively assist in the creation of answer set programs.

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。

↑