Rehearsing Answers to Probable Questions with Perspective-Taking
This addresses a specific need for professionals in presentation scenarios, but it is incremental as it builds on existing QA and LLM methods.
The paper tackled the underexplored problem of preparing answers to probable questions in professional oral presentations by using real-world QA transcripts between managers and analysts, finding that causal knowledge graphs and perspective-taking are important for generating effective responses with LLMs.
Question answering (QA) has been a long-standing focus in the NLP field, predominantly addressing reading comprehension and common sense QA. However, scenarios involving the preparation of answers to probable questions during professional oral presentations remain underexplored. In this paper, we pioneer the examination of this crucial yet overlooked topic by utilizing real-world QA conversation transcripts between company managers and professional analysts. We explore the proposed task using three causal knowledge graphs (KGs) and three large language models (LLMs). This work provides foundational insights into the application of LLMs in professional QA scenarios, highlighting the importance of causal KGs and perspective-taking in generating effective responses.