Effects of Different Prompts on the Quality of GPT-4 Responses to Dementia Care Questions
This work addresses prompt engineering for improving LLM outputs in healthcare, specifically for dementia caregivers, but is incremental as it explores a limited set of prompts and data.
The study investigated how different prompts affect GPT-4's response quality to dementia care questions, finding that response length varied significantly but quality scores were moderate, with average ratings around 3.0 out of 5 across 36 responses.
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 of details, totaling 12 prompt combinations. Next, we selected 3 social media posts containing complicated, real-world questions about dementia caregivers' challenges in 3 areas: memory loss and confusion, aggression, and driving. We then entered these posts into GPT-4, with our 12 prompts, to generate 12 responses per post, totaling 36 responses. We compared the word count of the 36 responses to explore potential differences in response length. Two experienced dementia care clinicians on our team assessed the response quality using a rating scale with 5 quality indicators: factual, interpretation, application, synthesis, and comprehensiveness (scoring range: 0-5; higher scores indicate higher quality).