Strategy-Induct: Task-Level Strategy Induction for Instruction Generation

ArXi:2605.20924v1 Announce Type: new Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction nstrates 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.