@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",
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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jain-etal-2024-rag">
<titleInfo>
<title>From RAG to Riches: Retrieval Interlaced with Sequence Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Palak</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Livio</namePart>
<namePart type="family">Baldini Soares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kwiatkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">jain-etal-2024-rag</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.502</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.502/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>8887</start>
<end>8904</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From RAG to Riches: Retrieval Interlaced with Sequence Generation
%A Jain, Palak
%A Baldini Soares, Livio
%A Kwiatkowski, Tom
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F jain-etal-2024-rag
%X 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.
%R 10.18653/v1/2024.emnlp-main.502
%U https://aclanthology.org/2024.emnlp-main.502/
%U https://doi.org/10.18653/v1/2024.emnlp-main.502
%P 8887-8904
Markdown (Informal)
[From RAG to Riches: Retrieval Interlaced with Sequence Generation](https://aclanthology.org/2024.emnlp-main.502/) (Jain et al., EMNLP 2024)
- From RAG to Riches: Retrieval Interlaced with Sequence Generation (Jain et al., EMNLP 2024)
ACL
- Palak Jain, Livio Baldini Soares, and Tom Kwiatkowski. 2024. From RAG to Riches: Retrieval Interlaced with Sequence Generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8887–8904, Miami, Florida, USA. Association for Computational Linguistics.