mlsanityData to 7 Oct 2026

Prompt Repetition Improves Non-Reasoning LLMs

arXiv 2512.14982 ↗First posted 17 Dec 2025cs.LG cs.AI cs.CLcited by 23

Not on the map. Why?

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.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 11 of its 18 references that are in the map. First posted on arXiv 17 Dec 2025.

Builds on

11 of 18 references.

References · 11

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  5. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  6. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  7. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  8. 2024Repetition Improves Language Model Embeddingscited by 70
  9. 2023Re-Reading Improves Reasoning in Large Language Modelscited by 37
  10. 2024Selective Attention Improves Transformercited by 26
  11. 2024Asking Again and Again: Exploring LLM Robustness to Repeated Questionscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 23.

23 papers.

Sort:

By area:

  1. 2026Human Cognition in Machines: A Unified Perspective of World Modelscited by 5
  2. 2026Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialoguecited by 4
  3. 2026On Test-Time Scaling for Vision-Language Modelscited by 4
  4. 2026Learning from Partial Chain-of-Thought via Truncated-Reasoning Self-Distillationcited by 3
  5. 2026Benchmark for Assessing Olfactory Perception of Large Language Modelscited by 3
  6. 2026Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysiscited by 3
  7. 2026Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detectorcited by 2
  8. 2026SCORE: Replacing Layer Stacking with Contractive Recurrent Depthcited by 2
  9. 2026Does Your VFM Speak Plant? The Botanical Grammar of Vision Foundation Models for Object Detectioncited by 1
  10. 2026M3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Taskscited by 1
  11. 2026ReasonLab: A Controlled and Auditable Evaluation of Prompting Techniques for Multiple-Choice QAcited by 1
  12. 2026sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebookcited by 0
11 more
  1. 2026Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectorscited by 0
  2. 2026Beyond Questions: Evaluating LLM's Knowledge Expressioncited by 0
  3. 2026Activation-Based Active Learning for In-Context Learning: Challenges and Insightscited by 0
  4. 2026mmPISA-bench: Do LLMs Reason Equally Well Across 43 Languages?cited by 0
  5. 2026PARTREP: Learning What to Repeat for Decoder-only LLMscited by 0
  6. 2026Understanding Tone-Dependent Inference Cost in Large Language Modelscited by 0
  7. 2026Instruction Duplication as an Inference-Time Control Primitivecited by 0
  8. 2026Some Tokens Behave like Magnets: Revealing Linguistic Organization in the Layers of Language Modelscited by 0
  9. 2026Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language Modelscited by 0
  10. 2026Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Modelscited by 0
  11. 2026Thinking Inertia: LLMs Keep Thinking When Told Not Tocited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation
  2. 2024Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning
  3. 2022Prompting GPT-3 To Be Reliable
  4. 2024LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language
  5. 2023GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts
  6. 2025Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
  7. 2024Does Prompt Formatting Have Any Impact on LLM Performance?
  8. 2024Think Beyond Size: Adaptive Prompting for More Effective Reasoning