Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models

TL;DR

This paper introduces LBS3, a curriculum learning-inspired prompting method for large language models that improves reasoning by progressively guiding models from easy to hard queries, reducing manual effort and enhancing performance.

Contribution

LBS3 is a novel prompt approach that mimics human learning by gradually increasing query difficulty, leading to better reasoning quality in LLMs without relying on external data.

Findings

LBS3 outperforms existing methods on reasoning tasks.

It reduces manual prompt engineering effort.

Achieves state-of-the-art results across various LLMs.

Abstract

While Chain of Thought (CoT) prompting approaches have significantly consolidated the reasoning capabilities of large language models (LLMs), they still face limitations that require extensive human effort or have performance needs to be improved. Existing endeavors have focused on bridging these gaps; however, these approaches either hinge on external data and cannot completely eliminate manual effort, or they fall short in effectively directing LLMs to generate high-quality exemplary prompts. To address the said pitfalls, we propose a novel prompt approach for automatic reasoning named \textbf{LBS3}, inspired by curriculum learning which better reflects human learning habits. Specifically, LBS3 initially steers LLMs to recall easy-to-hard proxy queries that are pertinent to the target query. Following this, it invokes a progressive strategy that utilizes exemplary prompts stemmed from easy-proxy queries to direct LLMs in solving hard-proxy queries, enabling the high-quality of the proxy solutions. Finally, our extensive experiments in various reasoning-intensive tasks with varying open- and closed-source LLMs show that LBS3 achieves strongly competitive performance compared to the SOTA baselines.