Prompt-based models have gathered a lot of attention from researchers due to their remarkable advancements in the fields of zero-shot and few-shot learning. Developing an effective prompt template plays a critical role. However, prior studies have mainly focused on prompt vocabulary selection or embedding initialization within a predefined template with the prompt position fixed. In this empirical study, we conduct the most comprehensive analysis to date of prompt position for diverse natural language process tasks. Our findings quantify the substantial impact prompt position has on model performance. We observe that the prompt position used in prior studies is often sub-optimal. These findings suggest prompt position optimisation as a valuable research direction to fill the gap in existing prompt engineering methodologies.

翻译：基于提示的模型因其在零样本和少样本学习领域的显著进展，引起了研究者的广泛关注。开发有效的提示模板至关重要。然而，先前的研究主要聚焦于在预设模板（且提示位置固定）下，进行提示词的选择或嵌入初始化。在这项实证研究中，我们对多种自然语言处理任务的提示位置进行了迄今为止最全面的分析。研究结果量化了提示位置对模型性能产生的显著影响。我们发现，先前研究中采用的提示位置往往并非最优。这些发现表明，提示位置优化可作为填补现有提示工程方法空白的宝贵研究方向。