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

TL;DR

This paper introduces Multiplex CoT, a self-reflective reasoning method for large language models that iteratively critiques and refines their own thought processes to enhance coherence and robustness.

Contribution

The paper proposes a novel double Chain of Thought approach enabling LLMs to self-review and improve reasoning without extra training, using simple prompt engineering.

Findings

Improved reasoning coherence and robustness in LLMs.

Effective implementation with prompt engineering in existing architectures.

Comparable to Learning-Refinement Model without additional training.

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.