RAG-end2end

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing1 result

Question AnsweringonSQuAD
Exact Match· 2021-06-22
40.02
best: 57.63 (Blended RAG)
SOTA
Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering arXiv:2106.11517