<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-prompt-optimization">
    <titleInfo>
        <title>Prompt Optimization for Relation Extraction using Reinforcement Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ying</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dong</namePart>
        <namePart type="family">Shuai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cui</namePart>
        <namePart type="family">Zibo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">TengQi</namePart>
        <namePart type="family">Ye</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gang</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Relation extraction is a fundamental task in information extraction. Still, existing supervised approaches rely heavily on large-scale annotated data, limiting their applicability in domain-specific and low-resource scenarios. Prompt-based methods with large language models provide a parameter-efficient alternative; however, their performance is susceptible to prompt design, which often requires extensive domain expertise and heuristic trial-and-error. We propose REPO, a reinforcement learning-based automated prompt optimization framework for domain relation extraction. REPO formulates prompt construction as a structured, sequential decision-making problem, optimizing prompt quality through interaction with a black-box LLM. To enable efficient and stable optimization, we introduce a two-stage framework comprising an initial prompt-construction stage that generates semantically grounded candidates and a DRL-based refinement stage that iteratively improves prompts within a constrained, domain-aware action space. We further design a composite evaluation metric that integrates extraction accuracy and semantic consistency to serve as a dense reward signal. Extensive experiments on multiple relation extraction datasets across medical, financial, legal, and news domains demonstrate that REPO consistently outperforms existing prompt-based methods and supervised baselines. Ablation studies further confirm the effectiveness and robustness of the proposed DRL-based prompt optimization strategy. Our code is available at https://github.com/dddong2-star/REPO.</abstract>
    <identifier type="citekey">liu-etal-2026-prompt-optimization</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.2100/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>42321</start>
            <end>42334</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prompt Optimization for Relation Extraction using Reinforcement Learning
%A Liu, Ying
%A Shuai, Dong
%A Zibo, Cui
%A Ye, TengQi
%A Wu, Gang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F liu-etal-2026-prompt-optimization
%X Relation extraction is a fundamental task in information extraction. Still, existing supervised approaches rely heavily on large-scale annotated data, limiting their applicability in domain-specific and low-resource scenarios. Prompt-based methods with large language models provide a parameter-efficient alternative; however, their performance is susceptible to prompt design, which often requires extensive domain expertise and heuristic trial-and-error. We propose REPO, a reinforcement learning-based automated prompt optimization framework for domain relation extraction. REPO formulates prompt construction as a structured, sequential decision-making problem, optimizing prompt quality through interaction with a black-box LLM. To enable efficient and stable optimization, we introduce a two-stage framework comprising an initial prompt-construction stage that generates semantically grounded candidates and a DRL-based refinement stage that iteratively improves prompts within a constrained, domain-aware action space. We further design a composite evaluation metric that integrates extraction accuracy and semantic consistency to serve as a dense reward signal. Extensive experiments on multiple relation extraction datasets across medical, financial, legal, and news domains demonstrate that REPO consistently outperforms existing prompt-based methods and supervised baselines. Ablation studies further confirm the effectiveness and robustness of the proposed DRL-based prompt optimization strategy. Our code is available at https://github.com/dddong2-star/REPO.
%U https://aclanthology.org/2026.findings-acl.2100/
%P 42321-42334

Markdown (Informal)

[Prompt Optimization for Relation Extraction using Reinforcement Learning](https://aclanthology.org/2026.findings-acl.2100/) (Liu et al., Findings 2026)

• Prompt Optimization for Relation Extraction using Reinforcement Learning (Liu et al., Findings 2026)

ACL

• Ying Liu, Dong Shuai, Cui Zibo, TengQi Ye, and Gang Wu. 2026. Prompt Optimization for Relation Extraction using Reinforcement Learning. In Findings of the Association for Computational Linguistics: ACL 2026, pages 42321–42334, San Diego, California, United States. Association for Computational Linguistics.