Follow Up Question Generation

Follow-up question generation (FQG) focuses on automatically creating relevant and informative subsequent questions based on an initial question and answer, aiming to deepen understanding or guide a conversation. Current research emphasizes developing models that leverage large language models (LLMs) and incorporate knowledge bases or process knowledge to generate more contextually appropriate and diverse follow-up questions, often evaluated using both automated and human-based metrics. This area is significant for improving conversational AI systems across various applications, including surveys, question answering, and even mental health triage, where carefully crafted follow-up questions are crucial for effective interaction.