From RAG to Riches: Retrieval Interlaced with Sequence Generation
Palak Jain, Livio Baldini Soares, Tom Kwiatkowski
Abstract
We present RICHES, a novel approach that interleaves retrieval with sequence generation tasks. RICHES offers an alternative to conventional RAG systems by eliminating the need for separate retriever and generator. It retrieves documents by directly decoding their contents, constrained on the corpus. Unifying retrieval with generation allows us to adapt to diverse new tasks via prompting alone. RICHES can work with any Instruction-tuned model, without additional training. It provides attributed evidence, supports multi-hop retrievals and interleaves thoughts to plan on what to retrieve next, all within a single decoding pass of the LLM. We demonstrate the strong performance of RICHES across ODQA tasks including attributed and multi-hop QA.
BibTeX
@inproceedings{jain-etal-2024-rag,
title = "From {RAG} to Riches: Retrieval Interlaced with Sequence Generation",
author = "Jain, Palak and
Baldini Soares, Livio and
Kwiatkowski, Tom",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.502/",
doi = "10.18653/v1/2024.emnlp-main.502",
pages = "8887--8904"
}