LPML: LLM-Prompting Markup Language for Mathematical Reasoning
This addresses mathematical reasoning errors in LLMs, offering an incremental improvement by combining existing methods in a novel way.
The paper tackles errors in LLM-generated mathematical reasoning by proposing a framework that integrates Chain-of-Thought with a Python REPL using an XML-like markup language, enabling ChatGPT to solve challenging problems with enhanced reasoning through zero-shot prompting.
In utilizing large language models (LLMs) for mathematical reasoning, addressing the errors in the reasoning and calculation present in the generated text by LLMs is a crucial challenge. In this paper, we propose a novel framework that integrates the Chain-of-Thought (CoT) method with an external tool (Python REPL). We discovered that by prompting LLMs to generate structured text in XML-like markup language, we could seamlessly integrate CoT and the external tool and control the undesired behaviors of LLMs. With our approach, LLMs can utilize Python computation to rectify errors within CoT. We applied our method to ChatGPT (GPT-3.5) to solve challenging mathematical problems and demonstrated that combining CoT and Python REPL through the markup language enhances the reasoning capability of LLMs. Our approach enables LLMs to write the markup language and perform advanced mathematical reasoning using only zero-shot prompting.