Score: 1
Prompt Repetition Improves Non-Reasoning LLMs
Published: December 17, 2025 |
arXiv ID: 2512.14982v1
By: Yaniv Leviathan, Matan Kalman, Yossi Matias
BigTech Affiliations:
Google
Potential Business Impact:
Repeating questions makes AI answer better without slowing down.
Business Areas:
Natural Language Processing
Artificial Intelligence, Data and Analytics, Software
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.
Similar Papers
89%
Asynchronous Reasoning: Training-Free Interactive Thinking LLMs
Machine Learning (CS)
Lets AI think and talk at the same time.
11 Dec 2025
2
89%
Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answers
Artificial Intelligence
Makes AI better at solving hard science problems.
2 May 2025
0
88%
Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention
Machine Learning (CS)
Teaches computers to solve hard math problems.
3 Aug 2025
1
Country of Origin
🇺🇸
United States
Page Count
12 pages
Category
Computer Science:
Machine Learning (CS)