Retrieval-augmented generation (RAG) methods encounter difficulties when addressing complex questions like multi-hop queries. While iterative retrieval methods improve performance by gathering additional information, current approaches often rely on multiple calls of large language models (LLMs). In this paper, we introduce EfficientRAG, an efficient retriever for multi-hop question answering. EfficientRAG iteratively generates new queries without the need for LLM calls at each iteration and filters out irrelevant information. Experimental results demonstrate that EfficientRAG surpasses existing RAG methods on three open-domain multi-hop question-answering datasets.

Suppose investors want to directly predict the future transaction price or ups and downs. In that case, the fatal assumption is that the training data set is consistent with the data distribution that has not occurred in the future. However, the natural world will not let us know whether the subsequent data distribution will change. Because of this, even if researchers add a moving window to the training process, it is inevitable that "machine learning obstacles-prediction delay" will occur. Our method can avoid "machine learning obstacles-prediction delay", We also propose auto trading by deep reinforcement learning. Our new article has the following contributions: 1. Our first contribution is not to make future predictions but to focus on the current "candlesticks pattern detection", such as Engulfing Pattern, Morning Star,.... 2. Our second contribution focuses on detecting trading entry and exit signals combined with related investment strategies.

Each award winner and received a B.S. in electrical received a certificate and a check engineering from the Technion Haifa for $2500.