<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-2025-leveraging">
    <titleInfo>
        <title>Leveraging Moment Injection for Enhanced Semi-supervised Natural Language Inference with Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Seo</namePart>
        <namePart type="given">Yeon</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-190-2</identifier>
    </relatedItem>
    <abstract>Natural Language Inference (NLI) is crucial for evaluating models’ Natural Language Understanding (NLU) and reasoning abilities. The development of NLI, in part, has been driven by the creation of large datasets, which require significant human effort. This has spurred interest in semi-supervised learning (SSL) that leverages both labeled and unlabeled data. However, the absence of hypotheses and class labels in NLI tasks complicates SSL. Prior work has used class-specific fine-tuned large language models (LLMs) to generate hypotheses and assign pseudo-labels but discarded many LLM-constructed samples during training to ensure the quality. In contrast, we propose to leverage all LLM-constructed samples by handling potentially noisy samples by injecting the moments of labeled samples during training to properly adjust the level of noise. Our method outperforms strong baselines on multiple NLI datasets in low-resource settings.</abstract>
    <identifier type="citekey">park-2025-leveraging</identifier>
    <identifier type="doi">10.18653/v1/2025.naacl-short.54</identifier>
    <location>
        <url>https://aclanthology.org/2025.naacl-short.54/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>641</start>
            <end>648</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Leveraging Moment Injection for Enhanced Semi-supervised Natural Language Inference with Large Language Models
%A Park, Seo Yeon
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-190-2
%F park-2025-leveraging
%X Natural Language Inference (NLI) is crucial for evaluating models’ Natural Language Understanding (NLU) and reasoning abilities. The development of NLI, in part, has been driven by the creation of large datasets, which require significant human effort. This has spurred interest in semi-supervised learning (SSL) that leverages both labeled and unlabeled data. However, the absence of hypotheses and class labels in NLI tasks complicates SSL. Prior work has used class-specific fine-tuned large language models (LLMs) to generate hypotheses and assign pseudo-labels but discarded many LLM-constructed samples during training to ensure the quality. In contrast, we propose to leverage all LLM-constructed samples by handling potentially noisy samples by injecting the moments of labeled samples during training to properly adjust the level of noise. Our method outperforms strong baselines on multiple NLI datasets in low-resource settings.
%R 10.18653/v1/2025.naacl-short.54
%U https://aclanthology.org/2025.naacl-short.54/
%U https://doi.org/10.18653/v1/2025.naacl-short.54
%P 641-648

Markdown (Informal)

[Leveraging Moment Injection for Enhanced Semi-supervised Natural Language Inference with Large Language Models](https://aclanthology.org/2025.naacl-short.54/) (Park, NAACL 2025)

• Leveraging Moment Injection for Enhanced Semi-supervised Natural Language Inference with Large Language Models (Park, NAACL 2025)

ACL

• Seo Yeon Park. 2025. Leveraging Moment Injection for Enhanced Semi-supervised Natural Language Inference with Large Language Models. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 641–648, Albuquerque, New Mexico. Association for Computational Linguistics.