Yaniv Leviathan, Matan Kalman, Yossi Matias
2025 · 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.
Metadata: arXiv. Abstracts retain their original authors’ rights.
Original HN comments, with labels from simple text rules. A label describes the whole comment and may miss context or irony. Read the discussion to make up your own mind. About the labels
4 selected excerpts · 4 total mentions
Really interesting paper, thanks for the share. The point their making in that paper reminds me of this paper some people shared around work earlier this year, https://arxiv.org/pdf/2512.14982 (Prompt Repetition Improves Non-Reasoning LLMs)... I wonder how OPs question would fare (or the questions presented in the paper you posted) given double repetition.
Actually not surprised. I guess this is for the same reason “say it twice” [1] is working. Because LLm are trained as causal language model, past token cannot attend to future token. One copy of the layer set solve this. [1]https://arxiv.org/html/2512.14982v1
"Prompt Repetition Improves Non-Reasoning LLMs " - https://arxiv.org/pdf/2512.14982 What instance of ChatGPT are you doing that with? (Reasoning?)
Interestingly, when I apply the "simply repeat the prompt" technique [1], Sonnet 4.6 on the website got it right every time, both with and without extended thinking. Not repeating the prompt got a mix of walk and drive answers. I love how prompt engineering is basically techno-alchemy 1: https://arxiv.org/pdf/2512.14982
More from the same topics.
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan +11
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition.
Tom B. Brown, Benjamin Mann, Nick Ryder +28
Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task.
Luca Beurer-Kellner, Beat Buesser, Ana-Maria Creţu +11
As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge.
Timo Schick, Jane Dwivedi-Yu, Roberto Dessì +5
Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale.