EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
This addresses inefficiencies in multi-hop question answering for users of RAG systems, though it appears incremental as it builds on iterative retrieval methods.
The paper tackles the problem of retrieval-augmented generation struggling with multi-hop queries by introducing EfficientRAG, which iteratively generates queries without LLM calls and filters irrelevant information, achieving superior performance on three open-domain datasets.
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.