Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shaier, Sagi, Sanz-Guerrero, Mario, von der Wense, Katharina
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.07923
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916650619502592
author Shaier, Sagi
Sanz-Guerrero, Mario
von der Wense, Katharina
author_facet Shaier, Sagi
Sanz-Guerrero, Mario
von der Wense, Katharina
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07923
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Asking Again and Again: Exploring LLM Robustness to Repeated Questions
Shaier, Sagi
Sanz-Guerrero, Mario
von der Wense, Katharina
Computation and Language
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.
title Asking Again and Again: Exploring LLM Robustness to Repeated Questions
topic Computation and Language
url https://arxiv.org/abs/2412.07923