Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering
2021-06-22Code Available0· sign in to hype
Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, Suranga Nanayakkara
Code Available — Be the first to reproduce this paper.
ReproduceCode
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| SQuAD | RAG-end2end | Exact Match | 40.02 | — | Unverified |