MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking

TL;DR

The paper addresses the challenge of limited self-reflection in large language models by proposing Multiplex CoT, a two-phase prompting approach that first generates an initial chain of thought and then critiques/refines it within a single inference, eliminating the need for additional training. It formalizes metrics for logical consistency, coherence, and error correction, and demonstrates gains across arithmetic and other reasoning tasks, indicating more robust and self-correcting outputs. The approach is designed to be easily integrated into existing LLM workflows, including practical Google Colab implementations, making it suitable for real-world decision-support applications. Overall, Multiplex CoT offers a scalable, prompt-based mechanism to enhance reasoning quality without altering model parameters.

Abstract

Recent advancements in large language models (LLMs) have demonstrated their impressive abilities in various reasoning and decision-making tasks. However, the quality and coherence of the reasoning process can still benefit from enhanced introspection and self-reflection. In this paper, we introduce Multiplex CoT (Chain of Thought), a method that enables LLMs to simulate a form of self-review while reasoning, by initiating double Chain of Thought (CoT) thinking. Multiplex CoT leverages the power of iterative reasoning, where the model generates an initial chain of thought and subsequently critiques and refines this reasoning with a second round of thought generation. This recursive approach allows for more coherent, logical, and robust answers, improving the overall decision-making process. We demonstrate how this method can be effectively implemented using simple prompt engineering in existing LLM architectures, achieving an effect similar to that of the Learning-Refinement Model (LRM) without the need for additional training. Additionally, we present a practical guide for implementing the method in Google Colab, enabling easy integration into real-world applications.