FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916616298561536 |
|---|---|
| author | Zhao, Xinping Zhong, Yan Sun, Zetian Hu, Xinshuo Liu, Zhenyu Li, Dongfang Hu, Baotian Zhang, Min |
| author_facet | Zhao, Xinping Zhong, Yan Sun, Zetian Hu, Xinshuo Liu, Zhenyu Li, Dongfang Hu, Baotian Zhang, Min |
| contents | Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful information used to facilitate the generation modules (a.k.a. generators). As such, generators' performance largely depends on the effectiveness and efficiency of retrievers. However, the widely used retrieval paradigm remains flat. It treats retrieval procedures as a one-off deal with constant granularity. Despite effectiveness, we argue that they suffer from two limitations: (1) flat retrieval exerts a significant burden on one retriever; (2) constant granularity limits the ceiling of retrieval performance. In this work, we propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency. Specifically, FunnelRAG establishes a progressive retrieval pipeline by collaborating coarse-to-fine granularity, large-to-small quantity, and low-to-high capacity, which can relieve the burden on one retriever and also promote the ceiling of retrieval performance. Extensive experiments manifest that FunnelRAG achieves comparable retrieval performance while the time overhead is reduced by nearly 40 percent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10293 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG Zhao, Xinping Zhong, Yan Sun, Zetian Hu, Xinshuo Liu, Zhenyu Li, Dongfang Hu, Baotian Zhang, Min Information Retrieval Computation and Language Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful information used to facilitate the generation modules (a.k.a. generators). As such, generators' performance largely depends on the effectiveness and efficiency of retrievers. However, the widely used retrieval paradigm remains flat. It treats retrieval procedures as a one-off deal with constant granularity. Despite effectiveness, we argue that they suffer from two limitations: (1) flat retrieval exerts a significant burden on one retriever; (2) constant granularity limits the ceiling of retrieval performance. In this work, we propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency. Specifically, FunnelRAG establishes a progressive retrieval pipeline by collaborating coarse-to-fine granularity, large-to-small quantity, and low-to-high capacity, which can relieve the burden on one retriever and also promote the ceiling of retrieval performance. Extensive experiments manifest that FunnelRAG achieves comparable retrieval performance while the time overhead is reduced by nearly 40 percent. |
| title | FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2410.10293 |