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 searching 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 Processing (NLP) tasks. Our findings quantify the substantial impact prompt position has on model performance. We observe that the prompt positions used in prior studies are often sub-optimal, and this observation is consistent even in widely used instruction-tuned models. These findings suggest prompt position optimisation as a valuable research direction to augment prompt engineering methodologies and prompt position-aware instruction tuning as a potential way to build more robust models in the future.

翻译：基于提示的模型因其在零样本和小样本学习领域的显著进展而备受研究者关注。开发有效的提示模板在其中起着关键作用。然而，先前的研究主要集中于在提示位置固定的预定义模板内进行提示词汇搜索或嵌入初始化。在本实证研究中，我们对不同自然语言处理（NLP）任务中的提示位置进行了迄今为止最全面的分析。我们的研究结果量化了提示位置对模型性能的重大影响。我们观察到，先前研究中使用的提示位置往往并非最优，这一观察结果即使在广泛使用的指令调优模型中也保持一致。这些发现表明，提示位置优化是增强提示工程方法论的一个有价值的研究方向，而提示位置感知的指令调优则是未来构建更稳健模型的潜在途径。