用类比思维增强小模型解物理题能力，减少幻觉。
Steps are all you need: Rethinking STEM Education with Prompt Engineering
- 用专家混合模型+类比提示，提升小模型数学推理
- 新方法使小模型在物理问答上超越基线大模型
- 适合想用开源模型做科学教育的开发者
少样本和思维链提示在物理问答任务中表现良好，但受限于大语言模型固有的数学能力不足及幻觉问题。通过采用专家混合（MoE）模型结合类比提示，我们实现了相比基线大模型的性能提升。同时调研了这些提示技术的局限性及其对模型表现的影响。此外，提出一种名为类比思维链（Analogical CoT）的提示方法，旨在让小型开源模型也能有效利用类比提示，解决其因缺乏专业训练数据而难以实现该能力的问题。
原文摘要 · Abstract (English)
Few shot and Chain-of-Thought prompting have shown promise when applied to Physics Question Answering Tasks, but are limited by the lack of mathematical ability inherent to LLMs, and are prone to hallucination. By utilizing a Mixture of Experts (MoE) Model, along with analogical prompting, we are able to show improved model performance when compared to the baseline on standard LLMs. We also survey the limits of these prompting techniques and the effects they have on model performance. Additionally, we propose Analogical CoT prompting, a prompting technique designed to allow smaller, open source models to leverage Analogical prompting, something they have struggled with, possibly due to a lack of specialist training data.
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。