Prompt Repetition Improves Non-Reasoning LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Leviathan, Yaniv, Kalman, Matan, Matias, Yossi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912770653421568
author Leviathan, Yaniv
Kalman, Matan
Matias, Yossi
author_facet Leviathan, Yaniv
Kalman, Matan
Matias, Yossi
contents When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14982
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt Repetition Improves Non-Reasoning LLMs
Leviathan, Yaniv
Kalman, Matan
Matias, Yossi
Machine Learning
Artificial Intelligence
Computation and Language
When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency.
title Prompt Repetition Improves Non-Reasoning LLMs
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2512.14982