Do prompt positions really matter?

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.