语言模型可以是逻辑求解器。

摘要

逻辑推理是人类智能的基本方面，也是问题解决和决策等任务的关键组成部分。最近的进展使得大型语言模型（LLMs）有可能展现推理能力，但复杂的逻辑推理仍然是一个挑战。目前最先进的增强求解器语言模型使用LLMs首先解析自然语言逻辑问题为符号表示，然后采用外部逻辑求解器接收符号表示并输出答案。尽管它们表现出色，但任何解析错误都将不可避免地导致外部逻辑求解器执行失败，无法回答逻辑问题。本文介绍了LoGiPT，一种新颖的语言模型，它直接模拟逻辑求解器的推理过程，并通过学习严格遵循求解器语法和语法来规避解析错误。LoGiPT在一个新构建的指令调整数据集上进行微调，该数据集揭示并完善了演绎求解器的隐形推理过程。在两个公共演绎推理数据集上的实验结果表明，LoGiPT在竞争性LLMs（如ChatGPT或GPT-4）上优于最先进的求解器增强型LLMs和少样本提示方法。

English

Logical reasoning is a fundamental aspect of human intelligence and a key component of tasks like problem-solving and decision-making. Recent advancements have enabled Large Language Models (LLMs) to potentially exhibit reasoning capabilities, but complex logical reasoning remains a challenge. The state-of-the-art, solver-augmented language models, use LLMs to parse natural language logical questions into symbolic representations first and then adopt external logical solvers to take in the symbolic representations and output the answers. Despite their impressive performance, any parsing errors will inevitably result in the failure of the execution of the external logical solver and no answer to the logical questions. In this paper, we introduce LoGiPT, a novel language model that directly emulates the reasoning processes of logical solvers and bypasses the parsing errors by learning to strict adherence to solver syntax and grammar. LoGiPT is fine-tuned on a newly constructed instruction-tuning dataset derived from revealing and refining the invisible reasoning process of deductive solvers. Experimental results on two public deductive reasoning datasets demonstrate that LoGiPT outperforms state-of-the-art solver-augmented LMs and few-shot prompting methods on competitive LLMs like ChatGPT or GPT-4.

语言模型可以是逻辑求解器。

Language Models can be Logical Solvers

摘要

Support