# Prompt Repetition Improves Non-Reasoning LLMs

arXiv: https://arxiv.org/abs/2512.14982 · HTML: https://mlsanity.com/paper/2512.14982/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Repetition Improves Language Model Embeddings](https://mlsanity.com/paper/2402.15449/) (2024)
- [Re-Reading Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2309.06275/) (2023)
- [Selective Attention Improves Transformer](https://mlsanity.com/paper/2410.02703/) (2024)
- [Asking Again and Again: Exploring LLM Robustness to Repeated Questions](https://mlsanity.com/paper/2412.07923/) (2024)

## Built on by (most cited first, 27 of 27)

- [Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue](https://mlsanity.com/paper/2603.11409/) (2026)
- [Human Cognition in Machines: A Unified Perspective of World Models](https://mlsanity.com/paper/2604.16592/) (2026)
- [Benchmark for Assessing Olfactory Perception of Large Language Models](https://mlsanity.com/paper/2604.00002/) (2026)
- [On Test-Time Scaling for Vision-Language Models](https://mlsanity.com/paper/2606.28864/) (2026)
- [Learning from Partial Chain-of-Thought via Truncated-Reasoning Self-Distillation](https://mlsanity.com/paper/2603.13274/) (2026)
- [Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis](https://mlsanity.com/paper/2605.03441/) (2026)
- [Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector](https://mlsanity.com/paper/2603.04663/) (2026)
- [SCORE: Replacing Layer Stacking with Contractive Recurrent Depth](https://mlsanity.com/paper/2603.10544/) (2026)
- [M3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks](https://mlsanity.com/paper/2606.05008/) (2026)
- [LLMs Contain Multitudes: How Deployment Context Reshapes Model-Level Preferences and Values](https://mlsanity.com/paper/2606.13944/) (2026)
- [Does Your VFM Speak Plant? The Botanical Grammar of Vision Foundation Models for Object Detection](https://mlsanity.com/paper/2604.09920/) (2026)
- [Beyond Questions: Evaluating the Stated Knowledge of LLMs](https://mlsanity.com/paper/2605.26937/) (2026)
- [ReasonLab: A Controlled and Auditable Evaluation of Prompting Techniques for Multiple-Choice QA](https://mlsanity.com/paper/2607.14109/) (2026)
- [sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook](https://mlsanity.com/paper/2603.13962/) (2026)
- [Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors](https://mlsanity.com/paper/2603.18593/) (2026)
- [Activation-Based Active Learning for In-Context Learning: Challenges and Insights](https://mlsanity.com/paper/2606.05134/) (2026)
- [mmPISA-bench: Do LLMs Reason Equally Well Across 43 Languages?](https://mlsanity.com/paper/2606.07069/) (2026)
- [PARTREP: Learning What to Repeat for Decoder-only LLMs](https://mlsanity.com/paper/2607.01792/) (2026)
- [Understanding Tone-Dependent Inference Cost in Large Language Models](https://mlsanity.com/paper/2607.23915/) (2026)
- [Instruction Duplication as an Inference-Time Control Primitive](https://mlsanity.com/paper/2609.04024/) (2026)
- [Some Tokens Behave like Magnets: Revealing Linguistic Organization in the Layers of Language Models](https://mlsanity.com/paper/2609.05743/) (2026)
- [Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language Models](https://mlsanity.com/paper/2609.15045/) (2026)
- [Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Models](https://mlsanity.com/paper/2609.39853/) (2026)
- [Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence](https://mlsanity.com/paper/2610.04791/) (2026)
- [Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files](https://mlsanity.com/paper/2610.09264/) (2026)
- [Thinking Inertia: LLMs Keep Thinking When Told Not To](https://mlsanity.com/paper/2610.11765/) (2026)
- [TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings](https://mlsanity.com/paper/2610.17065/) (2026)

## Abstract (arXiv)

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.