Ask Good Questions for Large Language Models
This work addresses the issue of inefficient information retrieval in dialog systems for users, but it appears incremental as it builds on existing methods like Item Response Theory.
The paper tackles the problem of large language models failing to provide accurate topic guidance due to an inability to discern user confusion in related concepts, resulting in improved information retrieval efficiency during question and answer processes.
Recent advances in large language models (LLMs) have significantly improved the performance of dialog systems, yet current approaches often fail to provide accurate guidance of topic due to their inability to discern user confusion in related concepts. To address this, we introduce the Ask-Good-Question (AGQ) framework, which features an improved Concept-Enhanced Item Response Theory (CEIRT) model to better identify users' knowledge levels. Our contributions include applying the CEIRT model along with LLMs to directly generate guiding questions based on the inspiring text, greatly improving information retrieval efficiency during the question & answer process. Through comparisons with other baseline methods, our approach outperforms by significantly enhencing the users' information retrieval experiences.