让大模型生成多个思考路径，提升零样本推理准确率。
Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
- 先生成多个不同思路的高阶推理方案
- 通过多方案归纳得到最终推理计划
- 无需大量采样，适合多种零样本任务
为解决标准链式思维提示中无引导推理路径的不稳定性，现有方法通过先提取单一推理策略来引导大语言模型。然而，每个问题仅依赖一种策略仍会限制跨任务性能。我们提出发散诱导提示（Diverge-to-Induce Prompting, DIP）框架：首先让大模型为每个问题生成多个多样化的高阶推理方案，再将每条方案展开为详细分步草稿计划，最后对这些草稿计划进行归纳整合形成最终计划。DIP在不依赖资源密集型采样的前提下提升了零样本推理准确率，实验表明其优于单策略提示，验证了多计划归纳在提示式推理中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。