Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning

TL;DR

Diverge-to-Induce Prompting (DIP) improves zero-shot reasoning in large language models by generating multiple diverse rationales and inducing a final plan, outperforming single-strategy methods.

Contribution

The paper introduces DIP, a novel multi-rationale induction framework that enhances reasoning accuracy without extensive sampling.

Findings

DIP outperforms single-strategy prompting in zero-shot reasoning tasks.

Generating multiple rationales improves the robustness of LLM reasoning.

Inducing a final plan from diverse drafts increases overall accuracy.

Abstract

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.