<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kong-etal-2024-prewrite">
    <titleInfo>
        <title>PRewrite: Prompt Rewriting with Reinforcement Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weize</namePart>
        <namePart type="family">Kong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Spurthi</namePart>
        <namePart type="family">Hombaiah</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mingyang</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qiaozhu</namePart>
        <namePart type="family">Mei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Bendersky</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a “trial and error” fashion that can be time consuming, ineffective, and sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications?To address these problems, we investigate automated prompt engineering in this paper. Specifically, we propose PRewrite, an automated method to rewrite an under-optimized prompt to a more effective prompt. We instantiate the prompt rewriter using an LLM. The rewriter LLM is trained using reinforcement learning to optimize the performance on a given downstream task. We conduct experiments on diverse benchmark datasets, which demonstrates the effectiveness of PRewrite.</abstract>
    <identifier type="citekey">kong-etal-2024-prewrite</identifier>
    <location>
        <url>https://aclanthology.org/2024.acl-short.54</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>594</start>
            <end>601</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PRewrite: Prompt Rewriting with Reinforcement Learning
%A Kong, Weize
%A Hombaiah, Spurthi
%A Zhang, Mingyang
%A Mei, Qiaozhu
%A Bendersky, Michael
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F kong-etal-2024-prewrite
%X Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a “trial and error” fashion that can be time consuming, ineffective, and sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications?To address these problems, we investigate automated prompt engineering in this paper. Specifically, we propose PRewrite, an automated method to rewrite an under-optimized prompt to a more effective prompt. We instantiate the prompt rewriter using an LLM. The rewriter LLM is trained using reinforcement learning to optimize the performance on a given downstream task. We conduct experiments on diverse benchmark datasets, which demonstrates the effectiveness of PRewrite.
%U https://aclanthology.org/2024.acl-short.54
%P 594-601

Markdown (Informal)

[PRewrite: Prompt Rewriting with Reinforcement Learning](https://aclanthology.org/2024.acl-short.54) (Kong et al., ACL 2024)

• PRewrite: Prompt Rewriting with Reinforcement Learning (Kong et al., ACL 2024)

ACL

• Weize Kong, Spurthi Hombaiah, Mingyang Zhang, Qiaozhu Mei, and Michael Bendersky. 2024. PRewrite: Prompt Rewriting with Reinforcement Learning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 594–601, Bangkok, Thailand. Association for Computational Linguistics.