Strategy-Induct: Task-Level Strategy Induction for Instruction Generation
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Incorporating Multimodal Information in Open-Domain Web Keyphrase Extraction
Open-domain Keyphrase extraction (KPE) on the Web is a fundamental yet complex NLP task with a wide range of practical applications within the field of Information Retrieval. In contrast to other document types, web page…
Information RetrievalKeyphrase ExtractionRetrievalDiverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
To address the instability of unguided reasoning paths in standard Chain-of-Thought prompting, recent methods guide large language models (LLMs) by first eliciting a single reasoning strategy. However, relying on just on…
Discontinuous PWM Strategy with Frequency Modulation for Vibration Reduction in Asynchronous Machines
The objective of this research is to mitigate vibrations in induction motors. To achieve this goal, a discontinuous pulse width modulation (PWM) control strategy based on carrier wave modulation is proposed for multileve…
Revealing Sequential Rationality and Forward Induction
Given a dynamic ordinal game, we deem a strategy sequentially rational if there exist a Bernoulli utility function and a conditional probability system with respect to which the strategy is a maximizer. We establish a co…
StrategyBench: Evaluating Explicit Strategy Induction in Large Language Models
As large language models are increasingly used in data-scarce and evolving task scenarios, few-shot in-context learning (ICL) has become a key paradigm for task adaptation. However, direct ICL often uses a small set of e…