English

Prompt Repetition Improves Non-Reasoning LLMs

Machine Learning 2025-12-18 v1 Artificial Intelligence Computation and Language
Authors: Yaniv Leviathan , Matan Kalman , Yossi Matias
View on arXiv ↗ PDF ↗

Abstract

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.

Keywords

prompt engineering large language model logical reasoning

Cite

@article{arxiv.2512.14982,
  title  = {Prompt Repetition Improves Non-Reasoning LLMs},
  author = {Yaniv Leviathan and Matan Kalman and Yossi Matias},
  journal= {arXiv preprint arXiv:2512.14982},
  year   = {2025}
}

Related papers

View all related →
Computation and Language · Computer Science
Asking Again and Again: Exploring LLM Robustness to Repeated Questions
Sagi Shaier, Mario Sanz-Guerrero, Katharina von der Wense
2025-03-13
Human-Computer Interaction · Computer Science
Prompt Engineering and the Effectiveness of Large Language Models in Enhancing Human Productivity
Rizal Khoirul Anam
2025-08-29
Information Retrieval · Computer Science
Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation
Genki Kusano, Kosuke Akimoto, Kunihiro Takeoka
2025-07-21
Computation and Language · Computer Science
The Importance of Prompt Tuning for Automated Neuron Explanations
Justin Lee, Tuomas Oikarinen, Arjun Chatha, Keng-Chi Chang +2
2023-10-12
Computation and Language · Computer Science
LatentPrompt: Optimizing Promts in Latent Space
Mateusz Bystroński, Grzegorz Piotrowski, Nitesh V. Chawla, Tomasz Kajdanowicz
2025-08-05
Computation and Language · Computer Science
Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance
Saurabh Srivastava, Chengyue Huang, Weiguo Fan, Ziyu Yao
2024-06-13
Artificial Intelligence · Computer Science
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Richmond Sin Jing Xuan, Rishabh Bhardwaj, Soujanya Poria
2026-05-08
Computation and Language · Computer Science
Reframing Instructional Prompts to GPTk's Language
Swaroop Mishra, Daniel Khashabi, Chitta Baral, Yejin Choi +1
2022-03-17
Computation and Language · Computer Science
Exploring Lottery Prompts for Pre-trained Language Models
Yulin Chen, Ning Ding, Xiaobin Wang, Shengding Hu +3
2023-06-01
Artificial Intelligence · Computer Science
On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models
Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati
2024-05-24
Computation and Language · Computer Science
The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning
Xi Ye, Greg Durrett
2022-10-14
Computation and Language · Computer Science
The language of prompting: What linguistic properties make a prompt successful?
Alina Leidinger, Robert van Rooij, Ekaterina Shutova
2023-11-06
Computation and Language · Computer Science
TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards
Andreea Nica, Ivan Zakazov, Nicolas Mario Baldwin, Saibo Geng +1
2025-07-25
Computation and Language · Computer Science
A NotSo Simple Way to Beat Simple Bench
Soham Sane, Angus McLean
2024-12-18
Computation and Language · Computer Science
Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks
Gregory Kang Ruey Lau, Wenyang Hu, Diwen Liu, Jizhuo Chen +2
2025-10-28
Artificial Intelligence · Computer Science
Reasoning Models Can Be Effective Without Thinking
Wenjie Ma, Jingxuan He, Charlie Snell, Tyler Griggs +2
2025-04-15
Computation and Language · Computer Science
PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning
Jiaru Zou, Mengyu Zhou, Tao Li, Shi Han +1
2024-10-17
Machine Learning · Computer Science
Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows
Orlando Marquez Ayala, Patrice Bechard, Emily Chen, Maggie Baird +1
2025-07-18
Computation and Language · Computer Science
RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners
Chi Hu, Yuan Ge, Xiangnan Ma, Hang Cao +4
2024-03-25
Computation and Language · Computer Science
Reflective Prompt Tuning through Language Model Function-Calling
Farima Fatahi Bayat, Moin Aminnaseri, Pouya Pezeshkpour, Estevam Hruschka
2026-05-22
Information Retrieval · Computer Science
Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems
Genki Kusano, Kosuke Akimoto, Kunihiro Takeoka
2024-12-20
Computation and Language · Computer Science
Metacognitive Prompting Improves Understanding in Large Language Models
Yuqing Wang, Yun Zhao
2024-03-22
Computation and Language · Computer Science
Batch Prompting: Efficient Inference with Large Language Model APIs
Zhoujun Cheng, Jungo Kasai, Tao Yu
2023-10-25
Computation and Language · Computer Science
Learning From Correctness Without Prompting Makes LLM Efficient Reasoner
Yuxuan Yao, Han Wu, Zhijiang Guo, Biyan Zhou +5
2024-07-19
Computation and Language · Computer Science
Prompt reinforcing for long-term planning of large language models
Hsien-Chin Lin, Benjamin Matthias Ruppik, Carel van Niekerk, Chia-Hao Shen +5
2026-05-19
R2 v1 2026-07-01T08:28:22.601Z