From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step

TL;DR

This paper introduces a method for training language models to internalize reasoning steps, enabling simpler reasoning processes and high accuracy on complex tasks like multiplication and math problem solving.

Contribution

The paper presents a finetuning approach that internalizes chain-of-thought reasoning in language models, reducing reliance on explicit intermediate steps.

Findings

GPT-2 Small achieves 99% accuracy on 9x9 multiplication

Model solves 4x4 multiplication with standard training

Mistral 7B achieves over 50% accuracy on GSM8K without intermediate steps

Abstract

When leveraging language models for reasoning tasks, generating explicit chain-of-thought (CoT) steps often proves essential for achieving high accuracy in final outputs. In this paper, we investigate if models can be taught to internalize these CoT steps. To this end, we propose a simple yet effective method for internalizing CoT steps: starting with a model trained for explicit CoT reasoning, we gradually remove the intermediate steps and finetune the model. This process allows the model to internalize the intermediate reasoning steps, thus simplifying the reasoning process while maintaining high performance. Our approach enables a GPT-2 Small model to solve 9-by-9 multiplication with up to 99% accuracy, whereas standard training cannot solve beyond 4-by-4 multiplication. Furthermore, our method proves effective on larger language models, such as Mistral 7B, achieving over 50% accuracy on GSM8K without producing any intermediate steps.