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 2404.01677cs.AIcs.CL
收藏

通过归结反演实现自然语言上可泛化且可信的逻辑推理

Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation

Research Center for Social Computing and Information Retrieval(社会计算与信息检索研究中心);Harbin Institute of Technology(哈尔滨工业大学);Beijing Academy of Artificial Intelligence(北京人工智能研究院)

Zhouhao Sun, Xiao Ding, Li Du, Bibo Cai, Jinglong Gao, Ting Liu, Qin Bing

AI总结:

针对 LLM 一阶逻辑推理的不完备问题,提出 GFaiR 框架,利用归结反演和反证法增强完备性,在复杂场景达到 SOTA 且推理过程忠实。

摘要:

大语言模型(LLM)已在多种自然语言推理任务中取得显著性能。然而,它们仍难以对以自然语言表达的形式逻辑理论执行一阶逻辑推理。这是因为以往基于 LLM 的推理系统存在理论上的不完备性问题。因此,其只能处理有限的一组简单推理问题,显著降低了泛化能力。为解决该问题,我们提出了一个名为 Generalizable and Faithful Reasoner(GFaiR)的新颖框架,引入了归结反演范式。归结反演能够通过扩展推理规则并运用反证法原则来求解所有一阶逻辑推理问题,因此引入归结反演可以提升系统的完备性。实验结果表明,我们的系统在复杂场景中取得了最先进性能,同时保持了在简单场景中的性能,优于以往工作。此外,我们观察到 GFaiR 对其推理过程是忠实可信的。

英文摘要:

Large language models (LLMs) have achieved significant performance in various natural language reasoning tasks. However, they still struggle with performing first-order logic reasoning over formal logical theories expressed in natural language. This is because the previous LLMs-based reasoning systems have the theoretical incompleteness issue. As a result, it can only address a limited set of simple reasoning problems, which significantly decreases their generalization ability. To address this issue, we propose a novel framework, named Generalizable and Faithful Reasoner (GFaiR), which introduces the paradigm of resolution refutation. Resolution refutation has the capability to solve all first-order logic reasoning problems by extending reasoning rules and employing the principle of proof by contradiction, so our system's completeness can be improved by introducing resolution refutation. Experimental results demonstrate that our system outperforms previous works by achieving state-of-the-art performances in complex scenarios while maintaining performances in simple scenarios. Besides, we observe that GFaiR is faithful to its reasoning process.

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。

↑