Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2411.07396 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917834624335872 |
|---|---|
| author | Leto, Alexandria Aguerrebere, Cecilia Bhati, Ishwar Willke, Ted Tepper, Mariano Vo, Vy Ai |
| author_facet | Leto, Alexandria Aguerrebere, Cecilia Bhati, Ishwar Willke, Ted Tepper, Mariano Vo, Vy Ai |
| contents | Retrieval-augmented generation (RAG) is a promising method for addressing some of the memory-related challenges associated with Large Language Models (LLMs). Two separate systems form the RAG pipeline, the retriever and the reader, and the impact of each on downstream task performance is not well-understood. Here, we work towards the goal of understanding how retrievers can be optimized for RAG pipelines for common tasks such as Question Answering (QA). We conduct experiments focused on the relationship between retrieval and RAG performance on QA and attributed QA and unveil a number of insights useful to practitioners developing high-performance RAG pipelines. For example, lowering search accuracy has minor implications for RAG performance while potentially increasing retrieval speed and memory efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07396 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Toward Optimal Search and Retrieval for RAG Leto, Alexandria Aguerrebere, Cecilia Bhati, Ishwar Willke, Ted Tepper, Mariano Vo, Vy Ai Computation and Language Retrieval-augmented generation (RAG) is a promising method for addressing some of the memory-related challenges associated with Large Language Models (LLMs). Two separate systems form the RAG pipeline, the retriever and the reader, and the impact of each on downstream task performance is not well-understood. Here, we work towards the goal of understanding how retrievers can be optimized for RAG pipelines for common tasks such as Question Answering (QA). We conduct experiments focused on the relationship between retrieval and RAG performance on QA and attributed QA and unveil a number of insights useful to practitioners developing high-performance RAG pipelines. For example, lowering search accuracy has minor implications for RAG performance while potentially increasing retrieval speed and memory efficiency. |
| title | Toward Optimal Search and Retrieval for RAG |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.07396 |