Distilling Many-Shot In-Context Learning into a Cheat Sheet
This addresses the computational bottleneck for practitioners using LLMs in downstream tasks, offering a practical alternative to many-shot and retrieval-based ICL.
The paper tackles the high computational cost of many-shot in-context learning in large language models by proposing cheat-sheet ICL, which distills many-shot examples into a concise textual summary, achieving comparable or better performance with far fewer tokens on challenging reasoning tasks.
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.