BloomWise: Enhancing Problem-Solving capabilities of Large Language Models using Bloom's-Taxonomy-Inspired Prompts

TL;DR

BloomWise is a prompting technique inspired by Bloom's taxonomy that guides large language models through cognitive levels to improve mathematical reasoning and explainability, showing significant performance gains.

Contribution

We introduce BloomWise, a novel cognitively-inspired prompting method that enhances LLMs' mathematical reasoning by mimicking human learning processes through structured cognitive levels.

Findings

Improves accuracy on five math reasoning datasets

Enhances explainability of LLM solutions

Effective across multiple reasoning tasks

Abstract

Despite the remarkable capabilities of large language models (LLMs) across a range of tasks, mathematical reasoning remains a challenging frontier. Motivated by the observation that humans learn more effectively when prompted not what to think but how to think, we introduce BloomWise, a cognitively-inspired prompting technique designed to enhance LLMs' performance on mathematical problem solving while making their solutions more explainable. BloomWise encourages LLMs to generate solutions - in the form of explanations - by progressing through a sequence of cognitive operations-from basic (e.g., remembering) to more advanced reasoning skills (e.g., evaluating) - mirroring how humans build understanding. The process iterates through these levels, halting early if a convergence criterion is met: specifically, if two or more consecutive levels yield the same answer, the solution from the earliest such level is output; otherwise, the process continues until all levels are completed. Through extensive experiments across five popular math reasoning datasets, we demonstrate the effectiveness of BloomWise. We also present comprehensive ablation studies to analyze the strengths of each component within our system.