Pregnant Questions: The Importance of Pragmatic Awareness in Maternal Health Question Answering
This addresses the risk of misinformation in high-stakes maternal health QA, though it is incremental as it builds on existing QA pipelines.
The paper tackled the problem of implicit false or harmful assumptions in user questions within maternal and infant health QA systems, by collecting a dataset of 2,727 pragmatic inferences from 500 questions and showing that incorporating these inferences makes responses more complete and mitigates harmful belief propagation.
Questions posed by information-seeking users often contain implicit false or potentially harmful assumptions. In a high-risk domain such as maternal and infant health, a question-answering system must recognize these pragmatic constraints and go beyond simply answering user questions, examining them in context to respond helpfully. To achieve this, we study assumptions and implications, or pragmatic inferences, made when mothers ask questions about pregnancy and infant care by collecting a dataset of 2,727 inferences from 500 questions across three diverse sources. We study how health experts naturally address these inferences when writing answers, and illustrate that informing existing QA pipelines with pragmatic inferences produces responses that are more complete, mitigating the propagation of harmful beliefs.