{"ID":2865806,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.20820","arxiv_id":"2509.20820","title":"Distilling Many-Shot In-Context Learning into a Cheat Sheet","abstract":"Recent advances in large language models (LLMs) enable effective in-context learning (ICL) with many-shot examples, but at the cost of high computational demand due to longer input tokens. To address this, we propose cheat-sheet ICL, which distills the information from many-shot ICL into a concise textual summary (cheat sheet) used as the context at inference time. Experiments on challenging reasoning tasks show that cheat-sheet ICL achieves comparable or better performance than many-shot ICL with far fewer tokens, and matches retrieval-based ICL without requiring test-time retrieval. These findings demonstrate that cheat-sheet ICL is a practical alternative for leveraging LLMs in downstream tasks.","short_abstract":"Recent advances in large language models (LLMs) enable effective in-context learning (ICL) with many-shot examples, but at the cost of high computational demand due to longer input tokens. To address this, we propose cheat-sheet ICL, which distills the information from many-shot ICL into a concise textual summary (chea...","url_abs":"https://arxiv.org/abs/2509.20820","url_pdf":"https://arxiv.org/pdf/2509.20820v1","authors":"[\"Ukyo Honda\",\"Soichiro Murakami\",\"Peinan Zhang\"]","published":"2025-09-25T07:07:46Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}