Retrieval-augmented generation (RAG) is usually integrated into large language models (LLMs) to mitigate hallucinations and knowledge obsolescence.Whereas, conventional onestep retrieve-and-read methods are insufficient for multi-hop question answering, facing challenges of retrieval semantic mismatching and the high cost in handling interdependent subquestions.In this paper, we propose Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (Q-DREAM).Q-DREAM consists of three key modules: (1) the Question Decomposition Module (QDM), which decomposes multi-hop questions into fine-grained subquestions; (2) the Subquestion Dependency Optimizer Module (SDOM), which models the interdependent relations of subquestions for better understanding; and (3) the Dynamic Passage Retrieval Module (DPRM), which aligns subquestions with relevant passages by optimizing the semantic embeddings.Experimental results across various benchmarks demonstrate that Q-DREAM significantly outperforms existing RAG methods, achieving state-of-the-art performance in both in-domain and out-of-domain settings.Notably, Q-DREAM also improves retrieval efficiency while maintaining high accuracy compared with recent baselines.

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 (ConvRAG) 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.

The role of driver is changing from controller to regulator as automated vehicles become more common. This change leads to deceased situation awareness (SA) because of passive engagement and increased non-driving related tasks (NDRT), and might affected drivers' takeover. This study designed a gamified prototype named Dangerous Slime to help drivers maintain SA during automated driving. Dangerous Slime turned surrounding cars into slimes that attacked drivers' cars; drivers need to response to these attacks, which increased their attention to nearby objects. Drivers can take the game as non-driving related tasks (NDRTs) during the whole automated driving process. When compared to NDRT of watching films, the game achieved an improvement in drivers' SA and positive user feedback. Moreover, the styles of games affect drivers' behavior and SA. This study revealed how the game influenced drivers' SA, and took a step toward improving the safety of automated driving in a pleasant way.