对比了提示中选项的排版格式对大模型表现的影响。
Effect of Selection Format on LLM Performance
- 用项目符号和纯文本两种方式呈现选项
- 项目符号格式整体提升模型准确率
- 研究为优化提示设计提供实证依据
本文探讨了大型语言模型（LLM）性能中的一个关键问题：分类任务选项在提示中的最优排版格式。通过一项广泛的实验研究，我们对比了两种选项格式——项目符号和纯英文描述——以评估其对模型性能的影响。研究发现，使用项目符号呈现选项通常能带来更好的结果，尽管存在个别例外情况。此外，本研究强调了持续探索选项格式对进一步提升模型性能的重要性。
原文摘要 · Abstract (English)
This paper investigates a critical aspect of large language model (LLM) performance: the optimal formatting of classification task options in prompts. Through an extensive experimental study, we compared two selection formats -- bullet points and plain English -- to determine their impact on model performance. Our findings suggest that presenting options via bullet points generally yields better results, although there are some exceptions. Furthermore, our research highlights the need for continued exploration of option formatting to drive further improvements in model performance.
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。