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 one strategy for each question can still limit performance across diverse tasks. We propose Diverge-to-Induce Prompting (DIP), a framework that first prompts an LLM to generate multiple diverse high-level rationales for each question. Each rationale is then elaborated into a detailed, step-by-step draft plan. Finally, these draft plans are induced into a final plan. DIP enhances zero-shot reasoning accuracy without reliance on resource-intensive sampling. Experiments show that DIP outperforms single-strategy prompting, demonstrating the effectiveness of multi-plan induction for prompt-based reasoning.
@article{arxiv.2602.08028,
title = {Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning},
author = {Po-Chun Chen and Hen-Hsen Huang and Hsin-Hsi Chen},
journal= {arXiv preprint arXiv:2602.08028},
year = {2026}
}