用心理疗法思路优化提示词，让小模型推理更准。
Dialectical Behavior Therapy Approach to LLM Prompting
- 借鉴辩证行为疗法构建分步对话式提示
- 小模型上准确率提升最高达16.2%
- 适合资源有限但需强推理的场景
大型语言模型在应用思维链（CoT）提示技术时，在各类推理任务上表现优异。CoT通过引导模型将任务分解为若干中间步骤并提供逐步示范。然而，复杂推理任务仍具挑战。本文提出一种受辩证行为疗法（DBT）启发的新提示策略。DBT是一种认知行为疗法，旨在帮助个体通过建立理性思维系统应对压力。我们将DBT的核心理念——塑造对话——应用于提示构建，并在不同数据集和参数量各异的大模型上进行实验。结果表明，采用DBT技巧构造的提示显著提升了小模型的表现：在80亿参数模型上，StrategyQA准确率提升7%，Aqua数据集提升4.8%；在140亿参数模型上，StrategyQA提升16.2%，GSM8K数据集提升5.3%。
原文摘要 · Abstract (English)
Large language models demonstrated state-of-the-art results on various reasoning tasks when applying the chain-of-thought (CoT) prompting technique. CoT prompting guides the model into breaking tasks into a few intermediate steps and provides step-by-step demonstrations. However, solving complex reasoning tasks remains a challenge. In this paper, we propose a novel prompting strategy inspired by Dialectical Behavioral Therapy (DBT). DBT, a form of cognitive-behavioral therapy, aims to help individuals cope with stress by developing a system of reasoning. We applied DBT's basic concepts of shaping dialog to construct prompts and conducted experiments on different datasets and LLMs with various numbers of parameters. Our results show that prompts crafted with DBT techniques significantly improve results on smaller models, achieving a 7% increase in accuracy on the StrategyQA, 4.8% on Aqua dataset using 8b parameters model, and a 16.2% increase on the StrategyQA, 5.3% on GSM8K dataset with 14b parameters model.
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。