让自然逻辑推理支持表格中的数值计算，提升事实验证的准确性与可解释性。
TabVer: Tabular Fact Verification with Natural Logic
- 将数字和算术函数纳入自然逻辑的集合论框架，实现数值推理的确定性证明
- 在FEVEROUS上达71.4准确率，比神经和符号模型均高3.4点
- 无需额外训练即可在TabFact上保持竞争力，适合需要透明推理的场景
表格事实验证需要符号推理模型，通过构建逻辑形式（如LISP风格程序）提升可验证性。然而，现有方法依赖结构良好表格，限制实际应用。当前文本推理中的自然逻辑范式通过建模主张与证据间的集合关系生成证明，具备灵活性与透明性，但难以处理表格中的算术运算。本文提出在自然逻辑中对数值和算术函数进行集合论解释，使算术表达式可融入确定性证明。利用大语言模型生成关于主张关键部分的问题，并在表格上执行相应函数获取答案，以生成算术表达式。在FEVEROUS的少样本设置下，准确率达71.4，优于全神经与符号模型3.4个百分点。在未微调的TabFact上，准确率领先0.5点，表现仍具竞争力。
原文摘要 · Abstract (English)
Fact verification on tabular evidence incentivises the use of symbolic reasoning models where a logical form is constructed (e.g. a LISP-style program), providing greater verifiability than fully neural approaches. However, these systems typically rely on well-formed tables, restricting their use in many scenarios. An emerging symbolic reasoning paradigm for textual evidence focuses on natural logic inference, which constructs proofs by modelling set-theoretic relations between a claim and its evidence in natural language. This approach provides flexibility and transparency but is less compatible with tabular evidence since the relations do not extend to arithmetic functions. We propose a set-theoretic interpretation of numerals and arithmetic functions in the context of natural logic, enabling the integration of arithmetic expressions in deterministic proofs. We leverage large language models to generate arithmetic expressions by generating questions about salient parts of a claim which are answered by executing appropriate functions on tables. In a few-shot setting on FEVEROUS, we achieve an accuracy of 71.4, outperforming both fully neural and symbolic reasoning models by 3.4 points. When evaluated on TabFact without any further training, our method remains competitive with an accuracy lead of 0.5 points.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。