<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nghiem-etal-2026-smarter">
    <titleInfo>
        <title>SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Huy</namePart>
        <namePart type="family">Nghiem</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Advik</namePart>
        <namePart type="family">Sachdeva</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hal</namePart>
        <namePart type="family">Daumé Iii</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>To address toxic content on social media, we introduce SMARTER, a data-efficient 2-stage framework for explainable content moderation using Large Language Models (LLMs). In Stage 1, we leverage LLMs’ own outputs to generate synthetic explanations for correct and incorrect labels, enabling preference optimization with minimal supervision. In Stage 2, we refine explanation quality through cross-model training, allowing weaker models to align with stronger ones. Experiments on 3 benchmarks (HateXplain, Latent Hate, Implicit Hate) show SMARTER achieves up to 13% macro-F1 improvement over few-shot baselines using only 6-57% of training data. Our framework offers a scalable strategy for low-data settings by harnessing LLMs’ self-improvement for explainable moderation.</abstract>
    <identifier type="citekey">nghiem-etal-2026-smarter</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.1584/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>34306</start>
            <end>34332</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
%A Nghiem, Huy
%A Sachdeva, Advik
%A Daumé Iii, Hal
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F nghiem-etal-2026-smarter
%X To address toxic content on social media, we introduce SMARTER, a data-efficient 2-stage framework for explainable content moderation using Large Language Models (LLMs). In Stage 1, we leverage LLMs’ own outputs to generate synthetic explanations for correct and incorrect labels, enabling preference optimization with minimal supervision. In Stage 2, we refine explanation quality through cross-model training, allowing weaker models to align with stronger ones. Experiments on 3 benchmarks (HateXplain, Latent Hate, Implicit Hate) show SMARTER achieves up to 13% macro-F1 improvement over few-shot baselines using only 6-57% of training data. Our framework offers a scalable strategy for low-data settings by harnessing LLMs’ self-improvement for explainable moderation.
%U https://aclanthology.org/2026.acl-long.1584/
%P 34306-34332

Markdown (Informal)

[SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models](https://aclanthology.org/2026.acl-long.1584/) (Nghiem et al., ACL 2026)

• SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models (Nghiem et al., ACL 2026)

ACL

• Huy Nghiem, Advik Sachdeva, and Hal Daumé Iii. 2026. SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 34306–34332, San Diego, California, United States. Association for Computational Linguistics.