notesum.ai
Published at November 29Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models
cs.CL
Released Date: November 29, 2024
Authors: Tian Yu1, Shaolei Zhang1, Yang Feng1
Aff.: 1Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS), University of Chinese Academy of Sciences, Beijing, China

| Methods | NQ | 2Wiki | TQA | PQA | HQA | WQ | AVG |
| EM | F1 | EM | F1 | F1 | EM | ||
| No Retrieval | |||||||
| Naive Gen | 22.6 | 33.9 | 55.7 | 21.7 | 28.4 | 18.8 | 30.2 |
| Single-time Retrieval | |||||||
| Standard RAG | 35.1 | 21.0 | 58.8 | 36.7 | 35.3 | 15.7 | 33.8 |
| IRCoT | 33.3 | 32.4 | 56.9 | 45.6 | 41.5 | 20.7 | 38.4 |
| REPLUG | 28.9 | 21.1 | 57.7 | 27.8 | 31.2 | 20.2 | 31.2 |
| RECOMP-abstractive | 33.1 | 32.4 | 56.4 | 39.9 | 37.5 | 20.2 | 36.6 |
| Selective-Context | 30.5 | 18.5 | 55.6 | 33.5 | 34.4 | 17.3 | 31.6 |
| Iterative Retrieval | |||||||
| FLARE | 22.5 | 33.9 | 55.8 | 20.7 | 28.0 | 20.2 | 30.2 |
| Self-RAG | 36.4 | 25.1 | 38.2 | 32.7 | 29.6 | 21.9 | 30.7 |
| Iter-RetGen | 36.8 | 21.6 | 60.1 | 37.9 | 38.3 | 18.2 | 35.5 |
| Ours (Autonomous Retrieval) | |||||||
| Auto-RAG | 37.9 | 48.9 | 60.9 | 47.8 | 44.9 | 25.1 | 44.3 |