@inproceedings{hoshi-etal-2023-ralle,
title = "{R}a{LL}e: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models",
author = "Hoshi, Yasuto and
Miyashita, Daisuke and
Ng, Youyang and
Tatsuno, Kento and
Morioka, Yasuhiro and
Torii, Osamu and
Deguchi, Jun",
editor = "Feng, Yansong and
Lefever, Els",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-demo.4",
doi = "10.18653/v1/2023.emnlp-demo.4",
pages = "52--69",
abstract = "Retrieval-augmented large language models (R-LLMs) combine pre-trained large language models (LLMs) with information retrieval systems to improve the accuracy of factual question-answering. However, current libraries for building R-LLMs provide high-level abstractions without sufficient transparency for evaluating and optimizing prompts within specific inference processes such as retrieval and generation. To address this gap, we present RaLLe, an open-source framework designed to facilitate the development, evaluation, and optimization of R-LLMs for knowledge-intensive tasks. With RaLLe, developers can easily develop and evaluate R-LLMs, improving hand-crafted prompts, assessing individual inference processes, and objectively measuring overall system performance quantitatively. By leveraging these features, developers can enhance the performance and accuracy of their R-LLMs in knowledge-intensive generation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoshi-etal-2023-ralle">
<titleInfo>
<title>RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yasuto</namePart>
<namePart type="family">Hoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Miyashita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youyang</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kento</namePart>
<namePart type="family">Tatsuno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuhiro</namePart>
<namePart type="family">Morioka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Osamu</namePart>
<namePart type="family">Torii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Deguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Retrieval-augmented large language models (R-LLMs) combine pre-trained large language models (LLMs) with information retrieval systems to improve the accuracy of factual question-answering. However, current libraries for building R-LLMs provide high-level abstractions without sufficient transparency for evaluating and optimizing prompts within specific inference processes such as retrieval and generation. To address this gap, we present RaLLe, an open-source framework designed to facilitate the development, evaluation, and optimization of R-LLMs for knowledge-intensive tasks. With RaLLe, developers can easily develop and evaluate R-LLMs, improving hand-crafted prompts, assessing individual inference processes, and objectively measuring overall system performance quantitatively. By leveraging these features, developers can enhance the performance and accuracy of their R-LLMs in knowledge-intensive generation tasks.</abstract>
<identifier type="citekey">hoshi-etal-2023-ralle</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-demo.4</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-demo.4</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>52</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models
%A Hoshi, Yasuto
%A Miyashita, Daisuke
%A Ng, Youyang
%A Tatsuno, Kento
%A Morioka, Yasuhiro
%A Torii, Osamu
%A Deguchi, Jun
%Y Feng, Yansong
%Y Lefever, Els
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F hoshi-etal-2023-ralle
%X Retrieval-augmented large language models (R-LLMs) combine pre-trained large language models (LLMs) with information retrieval systems to improve the accuracy of factual question-answering. However, current libraries for building R-LLMs provide high-level abstractions without sufficient transparency for evaluating and optimizing prompts within specific inference processes such as retrieval and generation. To address this gap, we present RaLLe, an open-source framework designed to facilitate the development, evaluation, and optimization of R-LLMs for knowledge-intensive tasks. With RaLLe, developers can easily develop and evaluate R-LLMs, improving hand-crafted prompts, assessing individual inference processes, and objectively measuring overall system performance quantitatively. By leveraging these features, developers can enhance the performance and accuracy of their R-LLMs in knowledge-intensive generation tasks.
%R 10.18653/v1/2023.emnlp-demo.4
%U https://aclanthology.org/2023.emnlp-demo.4
%U https://doi.org/10.18653/v1/2023.emnlp-demo.4
%P 52-69
Markdown (Informal)
[RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models](https://aclanthology.org/2023.emnlp-demo.4) (Hoshi et al., EMNLP 2023)
ACL