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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Po-Chun, Huang, Hen-Hsen, Chen, Hsin-Hsi
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918512515088384
author Chen, Po-Chun
Huang, Hen-Hsen
Chen, Hsin-Hsi
author_facet Chen, Po-Chun
Huang, Hen-Hsen
Chen, Hsin-Hsi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08028
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
Chen, Po-Chun
Huang, Hen-Hsen
Chen, Hsin-Hsi
Computation and Language
Artificial Intelligence
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.
title Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2602.08028