@inproceedings{lee-etal-2024-planrag,
title = "{P}lan{RAG}: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers",
author = "Lee, Myeonghwa and
An, Seonho and
Kim, Min-Soo",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.364",
pages = "6537--6555",
abstract = "In this paper, we conduct a study to utilize LLMs as a solution for decision making that requires complex data analysis. We define **Decision QA** as the task of answering the best decision, $d_{best}$, for a decision-making question $Q$, business rules $R$ and a database $D$. Since there is no benchmark that can examine Decision QA, we propose Decision QA benchmark, **DQA**. It has two scenarios, Locating and Building, constructed from two video games (Europa Universalis IV and Victoria 3) that have almost the same goal as Decision QA. To address Decision QA effectively, we also propose a new RAG technique called the *iterative plan-then-retrieval augmented generation* (**PlanRAG**). Our PlanRAG-based LM generates the plan for decision making as the first step, and the retriever generates the queries for data analysis as the second step. The proposed method outperforms the state-of-the-art iterative RAG method by 15.8{\%} in the Locating scenario and by 7.4{\%} in the Building scenario, respectively. We release our code and benchmark at https://github.com/myeon9h/PlanRAG.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2024-planrag">
<titleInfo>
<title>PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Myeonghwa</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seonho</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Soo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we conduct a study to utilize LLMs as a solution for decision making that requires complex data analysis. We define **Decision QA** as the task of answering the best decision, d_best, for a decision-making question Q, business rules R and a database D. Since there is no benchmark that can examine Decision QA, we propose Decision QA benchmark, **DQA**. It has two scenarios, Locating and Building, constructed from two video games (Europa Universalis IV and Victoria 3) that have almost the same goal as Decision QA. To address Decision QA effectively, we also propose a new RAG technique called the *iterative plan-then-retrieval augmented generation* (**PlanRAG**). Our PlanRAG-based LM generates the plan for decision making as the first step, and the retriever generates the queries for data analysis as the second step. The proposed method outperforms the state-of-the-art iterative RAG method by 15.8% in the Locating scenario and by 7.4% in the Building scenario, respectively. We release our code and benchmark at https://github.com/myeon9h/PlanRAG.</abstract>
<identifier type="citekey">lee-etal-2024-planrag</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.364</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>6537</start>
<end>6555</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers
%A Lee, Myeonghwa
%A An, Seonho
%A Kim, Min-Soo
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F lee-etal-2024-planrag
%X In this paper, we conduct a study to utilize LLMs as a solution for decision making that requires complex data analysis. We define **Decision QA** as the task of answering the best decision, d_best, for a decision-making question Q, business rules R and a database D. Since there is no benchmark that can examine Decision QA, we propose Decision QA benchmark, **DQA**. It has two scenarios, Locating and Building, constructed from two video games (Europa Universalis IV and Victoria 3) that have almost the same goal as Decision QA. To address Decision QA effectively, we also propose a new RAG technique called the *iterative plan-then-retrieval augmented generation* (**PlanRAG**). Our PlanRAG-based LM generates the plan for decision making as the first step, and the retriever generates the queries for data analysis as the second step. The proposed method outperforms the state-of-the-art iterative RAG method by 15.8% in the Locating scenario and by 7.4% in the Building scenario, respectively. We release our code and benchmark at https://github.com/myeon9h/PlanRAG.
%U https://aclanthology.org/2024.naacl-long.364
%P 6537-6555
Markdown (Informal)
[PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers](https://aclanthology.org/2024.naacl-long.364) (Lee et al., NAACL 2024)
ACL