<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wen-etal-2025-synthetic">
    <titleInfo>
        <title>On Synthetic Data Strategies for Domain-Specific Generative Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haoyang</namePart>
        <namePart type="family">Wen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiang</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiarong</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhiguo</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-251-0</identifier>
    </relatedItem>
    <abstract>This paper investigates synthetic data generation strategies in developing generative retrieval models for domain-specific corpora, thereby addressing the scalability challenges inherent in manually annotating in-domain queries. We study the data strategies for a two-stage training framework: in the first stage, which focuses on learning to decode document identifiers from queries, we investigate LLM-generated queries across multiple granularity (e.g. chunks, sentences) and domain-relevant search constraints that can better capture nuanced relevancy signals. In the second stage, which aims to refine document ranking through preference learning, we explore the strategies for mining hard negatives based on the initial model’s predictions. Experiments on public datasets over diverse domains demonstrate the effectiveness of our synthetic data generation and hard negative sampling approach.</abstract>
    <identifier type="citekey">wen-etal-2025-synthetic</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-long.392</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-long.392/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>7961</start>
            <end>7976</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On Synthetic Data Strategies for Domain-Specific Generative Retrieval
%A Wen, Haoyang
%A Guo, Jiang
%A Zhang, Yi
%A Jiang, Jiarong
%A Wang, Zhiguo
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F wen-etal-2025-synthetic
%X This paper investigates synthetic data generation strategies in developing generative retrieval models for domain-specific corpora, thereby addressing the scalability challenges inherent in manually annotating in-domain queries. We study the data strategies for a two-stage training framework: in the first stage, which focuses on learning to decode document identifiers from queries, we investigate LLM-generated queries across multiple granularity (e.g. chunks, sentences) and domain-relevant search constraints that can better capture nuanced relevancy signals. In the second stage, which aims to refine document ranking through preference learning, we explore the strategies for mining hard negatives based on the initial model’s predictions. Experiments on public datasets over diverse domains demonstrate the effectiveness of our synthetic data generation and hard negative sampling approach.
%R 10.18653/v1/2025.acl-long.392
%U https://aclanthology.org/2025.acl-long.392/
%U https://doi.org/10.18653/v1/2025.acl-long.392
%P 7961-7976

Markdown (Informal)

[On Synthetic Data Strategies for Domain-Specific Generative Retrieval](https://aclanthology.org/2025.acl-long.392/) (Wen et al., ACL 2025)

• On Synthetic Data Strategies for Domain-Specific Generative Retrieval (Wen et al., ACL 2025)

ACL

• Haoyang Wen, Jiang Guo, Yi Zhang, Jiarong Jiang, and Zhiguo Wang. 2025. On Synthetic Data Strategies for Domain-Specific Generative Retrieval. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7961–7976, Vienna, Austria. Association for Computational Linguistics.