<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-etal-2025-cuckoo">
    <titleInfo>
        <title>Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM’s Nest</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Letian</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zilong</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Feng</namePart>
        <namePart type="family">Yao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jingbo</namePart>
        <namePart type="family">Shang</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>Massive high-quality data, both pre-training raw texts and post-training annotations, have been carefully prepared to incubate advanced large language models (LLMs). In contrast, for information extraction (IE), pre-training data, such as BIO-tagged sequences, are hard to scale up. We show that IE models can act as free riders on LLM resources by reframing next-token prediction into extraction for tokens already present in the context. Specifically, our proposed next tokens extraction (NTE) paradigm learns a versatile IE model, Cuckoo, with 102.6M extractive data converted from LLM’s pre-training and post-training data. Under the few-shot setting, Cuckoo adapts effectively to traditional and complex instruction-following IE with better performance than existing pre-trained IE models. As a free rider, Cuckoo can naturally evolve with the ongoing advancements in LLM data preparation, benefiting from improvements in LLM training pipelines without additional manual effort.</abstract>
    <identifier type="citekey">peng-etal-2025-cuckoo</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-long.66</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-long.66/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>1301</start>
            <end>1315</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM’s Nest
%A Peng, Letian
%A Wang, Zilong
%A Yao, Feng
%A Shang, Jingbo
%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 peng-etal-2025-cuckoo
%X Massive high-quality data, both pre-training raw texts and post-training annotations, have been carefully prepared to incubate advanced large language models (LLMs). In contrast, for information extraction (IE), pre-training data, such as BIO-tagged sequences, are hard to scale up. We show that IE models can act as free riders on LLM resources by reframing next-token prediction into extraction for tokens already present in the context. Specifically, our proposed next tokens extraction (NTE) paradigm learns a versatile IE model, Cuckoo, with 102.6M extractive data converted from LLM’s pre-training and post-training data. Under the few-shot setting, Cuckoo adapts effectively to traditional and complex instruction-following IE with better performance than existing pre-trained IE models. As a free rider, Cuckoo can naturally evolve with the ongoing advancements in LLM data preparation, benefiting from improvements in LLM training pipelines without additional manual effort.
%R 10.18653/v1/2025.acl-long.66
%U https://aclanthology.org/2025.acl-long.66/
%U https://doi.org/10.18653/v1/2025.acl-long.66
%P 1301-1315

Markdown (Informal)

[Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM’s Nest](https://aclanthology.org/2025.acl-long.66/) (Peng et al., ACL 2025)

• Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM’s Nest (Peng et al., ACL 2025)

ACL

• Letian Peng, Zilong Wang, Feng Yao, and Jingbo Shang. 2025. Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM’s Nest. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1301–1315, Vienna, Austria. Association for Computational Linguistics.