EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929515859542016 |
|---|---|
| author | Zhuang, Ziyuan Zhang, Zhiyang Cheng, Sitao Yang, Fangkai Liu, Jia Huang, Shujian Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei Zhang, Qi |
| author_facet | Zhuang, Ziyuan Zhang, Zhiyang Cheng, Sitao Yang, Fangkai Liu, Jia Huang, Shujian Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei Zhang, Qi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04259 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EfficientRAG: Efficient Retriever for Multi-Hop Question Answering Zhuang, Ziyuan Zhang, Zhiyang Cheng, Sitao Yang, Fangkai Liu, Jia Huang, Shujian Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei Zhang, Qi Computation and Language Artificial Intelligence 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. |
| title | EfficientRAG: Efficient Retriever for Multi-Hop Question Answering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2408.04259 |