Effect of Selection Format on LLM Performance
This addresses a specific prompt engineering problem for LLM users, but it is incremental as it focuses on a narrow formatting aspect.
The paper investigated how formatting classification task options in prompts affects large language model performance, finding that bullet points generally yield better results than plain 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.