Asking Again and Again: Exploring LLM Robustness to Repeated Questions

TL;DR

This paper examines whether repeating questions in prompts affects large language models' performance, finding that while repetition can improve accuracy slightly, the effects are not statistically significant across various models and datasets.

Contribution

It systematically evaluates the impact of question repetition within prompts on multiple LLMs across different datasets, providing insights into prompt design strategies.

Findings

Repetition can increase accuracy by up to 6%.

No statistically significant effect of repetition on model performance.

Repetition alone does not substantially improve LLM output quality.

Abstract

This study investigates whether repeating questions within prompts influences the performance of large language models (LLMs). We hypothesize that reiterating a question within a single prompt might enhance the model's focus on key elements of the query. We evaluate five recent LLMs -- including GPT-4o-mini, DeepSeek-V3, and smaller open-source models -- on three reading comprehension datasets under different prompt settings, varying question repetition levels (1, 3, or 5 times per prompt). Our results demonstrate that question repetition can increase models' accuracy by up to $6\%$. However, across all models, settings, and datasets, we do not find the result statistically significant. These findings provide insights into prompt design and LLM behavior, suggesting that repetition alone does not significantly impact output quality.