arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.00830cs.CLcs.AI
收藏

LLM+AL:桥接大语言模型与动作语言以实现复杂的动作推理

LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actions

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

Adam Ishay, Joohyung Lee

AI总结:

本文提出LLM+AL方法,将大语言模型的自然语言理解与动作语言的符号推理结合,在复杂动作推理中仅需少量人工纠正即可持续得到正确答案,并支持动作语言的自动生成。

摘要:

大语言模型(LLMs)在各种智能任务中取得了显著进展,但在需要系统化搜索的复杂动作推理任务上仍然表现不佳。为了解决这一局限,我们提出了一种方法,将LLMs的自然语言理解能力与动作语言的符号推理优势相结合。我们的方法称为“LLM+AL”,它利用LLM在语义解析和常识知识生成方面的优势,以及动作语言在基于编码知识进行自动推理方面的专长。我们使用复杂动作推理基准,将LLM+AL与最先进的LLMs(包括ChatGPT-4、Claude 3 Opus、Gemini Ultra 1.0和o1-preview)进行了比较。我们的研究结果表明,尽管所有方法都会出现错误,但LLM+AL在相对较少的人工纠正下,能够持续得到正确答案,而单独的LLMs即使有人工反馈也无法改进。LLM+AL还有助于动作语言的自动生成。

英文摘要:

Large Language Models (LLMs) have made significant strides in various intelligent tasks but still struggle with complex action reasoning tasks that require systematic search. To address this limitation, we propose a method that bridges the natural language understanding capabilities of LLMs with the symbolic reasoning strengths of action languages. Our approach, termed "LLM+AL," leverages the LLM's strengths in semantic parsing and commonsense knowledge generation alongside the action language's proficiency in automated reasoning based on encoded knowledge. We compare LLM+AL against state-of-the-art LLMs, including ChatGPT-4, Claude 3 Opus, Gemini Ultra 1.0, and o1-preview, using benchmarks for complex reasoning about actions. Our findings indicate that, although all methods exhibit errors, LLM+AL, with relatively minimal human corrections, consistently leads to correct answers, whereas standalone LLMs fail to improve even with human feedback. LLM+AL also contributes to automated generation of action languages.

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。

↑