Effects of Different Prompts on the Quality of GPT-4 Responses to Dementia Care Questions

arXiv:2404.08674v1 Announce Type: new
Abstract: Evidence suggests that different prompts lead large language models (LLMs) to generate responses with varying quality. Yet, little is known about prompts' effects on response quality in healthcare domains. In this exploratory study, we address this gap, focusing on a specific healthcare domain: dementia caregiving. We first developed an innovative prompt template with three components: (1) system prompts (SPs) featuring 4 different roles; (2) an initialization prompt; and (3) task prompts (TPs) specifying different levels …

abstract arxiv cs.ai cs.cl cs.hc dementia domains effects evidence exploratory gap generate gpt gpt-4 healthcare language language models large language large language models llms prompts quality questions responses study type