Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked?

TL;DR

This paper investigates how different question formats affect the reasoning accuracy of large language models, revealing significant performance variations and factors influencing their reasoning abilities.

Contribution

It provides a systematic analysis of the impact of question types, options, and wording on LLM reasoning performance, an area previously unexplored.

Findings

Performance varies significantly across question types.

Reasoning accuracy does not always match final answer accuracy.

Question format, options, and wording influence LLM performance.

Abstract

Large Language Models (LLMs) have been evaluated using diverse question types, e.g., multiple-choice, true/false, and short/long answers. This study answers an unexplored question about the impact of different question types on LLM accuracy on reasoning tasks. We investigate the performance of five LLMs on three different types of questions using quantitative and deductive reasoning tasks. The performance metrics include accuracy in the reasoning steps and choosing the final answer. Key Findings: (1) Significant differences exist in LLM performance across different question types. (2) Reasoning accuracy does not necessarily correlate with the final selection accuracy. (3) The number of options and the choice of words, influence LLM performance.