Unified Active Retrieval for Retrieval Augmented Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917793466679296 |
|---|---|
| author | Cheng, Qinyuan Li, Xiaonan Li, Shimin Zhu, Qin Yin, Zhangyue Shao, Yunfan Li, Linyang Sun, Tianxiang Yan, Hang Qiu, Xipeng |
| author_facet | Cheng, Qinyuan Li, Xiaonan Li, Shimin Zhu, Qin Yin, Zhangyue Shao, Yunfan Li, Linyang Sun, Tianxiang Yan, Hang Qiu, Xipeng |
| contents | In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Therefore, determining whether to retrieve is crucial for RAG, which is usually referred to as Active Retrieval. However, existing active retrieval methods face two challenges: 1. They usually rely on a single criterion, which struggles with handling various types of instructions. 2. They depend on specialized and highly differentiated procedures, and thus combining them makes the RAG system more complicated and leads to higher response latency. To address these challenges, we propose Unified Active Retrieval (UAR). UAR contains four orthogonal criteria and casts them into plug-and-play classification tasks, which achieves multifaceted retrieval timing judgements with negligible extra inference cost. We further introduce the Unified Active Retrieval Criteria (UAR-Criteria), designed to process diverse active retrieval scenarios through a standardized procedure. Experiments on four representative types of user instructions show that UAR significantly outperforms existing work on the retrieval timing judgement and the performance of downstream tasks, which shows the effectiveness of UAR and its helpfulness to downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12534 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unified Active Retrieval for Retrieval Augmented Generation Cheng, Qinyuan Li, Xiaonan Li, Shimin Zhu, Qin Yin, Zhangyue Shao, Yunfan Li, Linyang Sun, Tianxiang Yan, Hang Qiu, Xipeng Computation and Language In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Therefore, determining whether to retrieve is crucial for RAG, which is usually referred to as Active Retrieval. However, existing active retrieval methods face two challenges: 1. They usually rely on a single criterion, which struggles with handling various types of instructions. 2. They depend on specialized and highly differentiated procedures, and thus combining them makes the RAG system more complicated and leads to higher response latency. To address these challenges, we propose Unified Active Retrieval (UAR). UAR contains four orthogonal criteria and casts them into plug-and-play classification tasks, which achieves multifaceted retrieval timing judgements with negligible extra inference cost. We further introduce the Unified Active Retrieval Criteria (UAR-Criteria), designed to process diverse active retrieval scenarios through a standardized procedure. Experiments on four representative types of user instructions show that UAR significantly outperforms existing work on the retrieval timing judgement and the performance of downstream tasks, which shows the effectiveness of UAR and its helpfulness to downstream tasks. |
| title | Unified Active Retrieval for Retrieval Augmented Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.12534 |