Balancing Precision and Generalization: Dynamic Instruction Generation for Model Adaptive Zero-Shot Reasoning in LLMs
Year: 2025
Type: conference-paper
Abstract: Current research shows that providing instructions to guide Large Language Models (LLMs) improves reasoning tasks, but existing methods struggle to balance accuracy and generalization. Manually crafted instructions tailored to specific LLMs and tasks improve performance but reduce generalizability, while more general instructions lack detail and lower performance. To address this, we propose a dynamic instruction-generation method using an Instruction-Generation Prompt (IGP). IGP categorizes problems into domains and integrates the model's capabilities to generate detailed task-specific instructions, resulting in a comprehensive plan. This approach achieves high precision with general prompts without requiring in-depth knowledge of LLMs or tasks. We validated our method across five LLMs and ten datasets in three task categories. Our dynamically generated instructions outperformed traditionally handcrafted, LLM-specific instructions across various LLMs and tasks.
Authors: Ruihan Zhu, Bo Wang, Dongming Zhao, Jing Liu, Ruifang He, Yuexian Hou
Institutions: Tianjin University, China Mobile (China)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4412376960