无需答案标签，仅用问题就能生成高质量指令。
Strategy-Induct: Task-Level Strategy Induction for Instruction Generation
- 通过让模型生成解题思路，构建问题与策略配对。
- 在多个任务上优于现有最先进方法，提升推理性能。
- 适合需要高效指令设计的AI研究者与开发者。
设计有效的任务级提示对提升大语言模型（LLMs）性能至关重要。尽管先前的指令归纳工作表明，模型可在少量示例下推断出更优指令，但现有方法通常依赖输入-输出对，而获取标注答案往往困难或成本高昂。为解决这一局限，我们提出Strategy-Induct框架，仅基于少量示例问题即可生成任务级指令，无需标注答案。该方法首先引导模型为每个问题生成明确的推理策略，形成（策略，问题）配对；再利用这些配对归纳出指导推理的任务指令。在多个任务和不同模型规模上的实验表明，Strategy-Induct在仅有问题的设置下优于当前最优方法。此外，我们发现联合使用大语言模型与大推理模型，在指令生成与推理阶段可进一步提升性能。
原文摘要 · Abstract (English)
Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs can infer better instructions with limited examples, existing approaches often rely on input-output pairs, where obtaining labeled answers can be difficult or costly. To address this limitation, we propose Strategy-Induct, a framework that derives task-level instructions solely from a small set of example questions without requiring labeled answers. Our approach first prompts the model to generate explicit reasoning strategies for each question, forming (strategy, question) pairs. These pairs are then used to induce a task instruction that guides reasoning. Experiments across multiple tasks and model scales demonstrate that Strategy-Induct outperforms state-of-the-art methods in question-only settings. Furthermore, we observe that jointly utilizing LLMs and Large Reasoning Models across task instruction generation and inference may lead to further performance improvements.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。