Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913532333785088 |
|---|---|
| author | Siriwardhana, Shamane Weerasekera, Rivindu Wen, Elliott Nanayakkara, Suranga |
| author_facet | Siriwardhana, Shamane Weerasekera, Rivindu Wen, Elliott Nanayakkara, Suranga |
| contents | In this paper, we illustrate how to fine-tune the entire Retrieval Augment Generation (RAG) architecture in an end-to-end manner. We highlighted the main engineering challenges that needed to be addressed to achieve this objective. We also compare how end-to-end RAG architecture outperforms the original RAG architecture for the task of question answering. We have open-sourced our implementation in the HuggingFace Transformers library. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_11517 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering Siriwardhana, Shamane Weerasekera, Rivindu Wen, Elliott Nanayakkara, Suranga Information Retrieval Artificial Intelligence Computation and Language In this paper, we illustrate how to fine-tune the entire Retrieval Augment Generation (RAG) architecture in an end-to-end manner. We highlighted the main engineering challenges that needed to be addressed to achieve this objective. We also compare how end-to-end RAG architecture outperforms the original RAG architecture for the task of question answering. We have open-sourced our implementation in the HuggingFace Transformers library. |
| title | Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering |
| topic | Information Retrieval Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2106.11517 |