arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.08415cs.CLcs.LO
收藏

FSLI:一种用于一维排序推理的可解释形式语义系统

FSLI: An Interpretable Formal Semantic System for One-Dimensional Ordering Inference

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Maha Alkhairy, Vincent Homer, Brendan O'Connor

AI总结:

FSLI将自然语言排序推理转化为一阶逻辑,通过基于组合语义的解析算法和约束逻辑编程实现可解释的符号演绎,在BIG-bench上达100%准确率并优于LLM基线。

摘要:

我们开发了一个系统,通过将自然语言前提和候选陈述转化为一阶逻辑来解决逻辑演绎的一维排序问题。该系统建立在Heim和Kratzer基于句法的组合语义规则之上,并利用lambda演算,我们开发了一种语义解析算法,该算法包含抽象类型、模板化规则以及一个动态组件,用于在由输入构建的上下文中解释实体。生成的逻辑形式通过约束逻辑编程执行,以确定哪些候选陈述可以从前提中逻辑演绎出来。该符号系统,即形式语义逻辑推理器(FSLI),为自然语言逻辑演绎提供了一个形式上有依据、语言学驱动的系统。我们在合成和衍生的逻辑演绎问题上对其进行了评估。FSLI在BIG-bench的逻辑演绎任务上达到了100%的准确率,在AR-LSAT的句法简化子集上达到了88%的准确率,优于LLM基线o1-preview。虽然当前自然语言推理的研究侧重于神经语言模型,但FSLI突显了有原则的、可解释的系统在NLP中用于符号逻辑演绎的潜力。

英文摘要:

We develop a system for solving logical deduction one-dimensional ordering problems by transforming natural language premises and candidate statements into first-order logic. Building on Heim and Kratzer's syntax-based compositional semantic rules which utilizes lambda calculus, we develop a semantic parsing algorithm with abstract types, templated rules, and a dynamic component for interpreting entities within a context constructed from the input. The resulting logical forms are executed via constraint logic programming to determine which candidate statements can be logically deduced from the premises. The symbolic system, the Formal Semantic Logic Inferer (FSLI), provides a formally grounded, linguistically driven system for natural language logical deduction. We evaluate it on both synthetic and derived logical deduction problems. FSLI achieves 100% accuracy on BIG-bench's logical deduction task and 88% on a syntactically simplified subset of AR-LSAT outperforming an LLM baseline, o1-preview. While current research in natural language reasoning emphasizes neural language models, FSLI highlights the potential of principled, interpretable systems for symbolic logical deduction in NLP.

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。

↑