Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check
This addresses the challenge of making RAG effective for complex conversational settings, which is an incremental improvement over existing single-round RAG methods.
The paper tackles the problem of adapting Retrieval-Augmented Generation (RAG) to conversational question answering, where questions depend on preceding context, by proposing a conversation-level approach with fine-grained retrieval and self-check. The result shows great advantages over state-of-the-art baselines in experiments, and the authors release a new Chinese CQA dataset to facilitate further research.
Retrieval-Augmented Generation (RAG) aims to generate more reliable and accurate responses, by augmenting large language models (LLMs) with the external vast and dynamic knowledge. Most previous work focuses on using RAG for single-round question answering, while how to adapt RAG to the complex conversational setting wherein the question is interdependent on the preceding context is not well studied. In this paper, we propose a conversation-level RAG approach, which incorporates fine-grained retrieval augmentation and self-check for conversational question answering (CQA). In particular, our approach consists of three components, namely conversational question refiner, fine-grained retriever and self-check based response generator, which work collaboratively for question understanding and relevant information acquisition in conversational settings. Extensive experiments demonstrate the great advantages of our approach over the state-of-the-art baselines. Moreover, we also release a Chinese CQA dataset with new features including reformulated question, extracted keyword, retrieved paragraphs and their helpfulness, which facilitates further researches in RAG enhanced CQA.