arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.06114cs.CLcs.AI
收藏

在演绎推理中显式化隐含前提

Making Implicit Premises Explicit in Logical Understanding of Enthymemes

University College London(伦敦大学学院)

Xuyao Feng, Anthony Hunter

AI总结:

本文提出了一种整合大型语言模型和神经符号推理器的管道,用于将隐含前提显式化并解码逻辑蕴含。

摘要:

现实中的文本和对话中的论证通常是 enthymemes(即其中某些前提和/或主张是隐含的)。自然语言处理(NLP)方法可以潜在地识别文本中的 enthymemes,但无法解码其底层逻辑,而基于逻辑的方法则假设有一个包含足够公式知识库,可以通过归谬法解码。因此,缺乏将 enthymeme 的文本组件转化为逻辑论证并生成解码所需逻辑公式,从而展示逻辑蕴含的系统方法。为了解决这个问题,我们提出了一种管道,整合:(1)一个大型语言模型(LLM)根据显式前提和主张生成中间隐含前提;(2)另一个 LLM 将自然语言翻译成逻辑公式;(3)基于 SAT 解析器的神经符号推理器来确定蕴含性。我们在两个 enthymeme 数据集中评估了我们的管道,展示了在选择正确隐含前提方面的有希望的表现,通过精确率、召回率、F1 分数和准确性来衡量。

英文摘要:

Real-world arguments in text and dialogues are normally enthymemes (i.e. some of their premises and/or claims are implicit). Natural language processing (NLP) methods for handling enthymemes can potentially identify enthymemes in text but they do not decode their underlying logic, whereas logic-based approaches for handling them assume a knowledgebase with sufficient formulae that can be used to decode them via abduction. There is therefore a lack of a systematic method for translating textual components of an enthymeme into a logical argument and generating the logical formulae required for their decoding, and thereby showing logical entailment. To address this, we propose a pipeline that integrates: (1) a large language model (LLM) to generate intermediate implicit premises based on the explicit premise and claim; (2) another LLM to translate the natural language into logical formulas; and (3) a neuro-symbolic reasoner based on a SAT solver to determine entailment. We evaluate our pipeline on two enthymeme datasets, demonstrating promising performance in selecting the correct implicit premise, as measured by precision, recall, F1-score, and accuracy.

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。

↑