<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="estuar-2026-team">
    <titleInfo>
        <title>Team Gazoo! at #SMM4H-HeaRD 2026: Zero-Training NER via Iterative LLM Prompt Self-Optimization for Opioid Impact Span Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Diego</namePart>
        <namePart type="family">Estuar</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 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Guillermo</namePart>
            <namePart type="family">Lopez-Garcia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Graciela</namePart>
            <namePart type="family">Gonzalez-Hernandez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-432-3</identifier>
    </relatedItem>
    <abstract>This paper describes the system submitted by Team Gazoo! for Task 7 of the #SMM4H-HeaRD 2026 shared task on detecting self-reported clinical and social impacts of nonmedical opioid use in social media text. We present a zero-training, prompt-only approach that uses a large language model (GPT-5.4) with structured few-shot prompting and autonomous, iterative rule optimization. Our system encodes a domain-specific entity ontology, three core decision rules, and 65 cognitively organized few-shot examples into a single prompt, with BIO constraint enforcement applied as post-processing. Crucially, the prompt itself is refined by the LLM: at each iteration the model analyzes its own errors and proposes targeted edits to its rules and examples. Through 18 such self-refinement cycles, our system achieved an F1-Strict of 0.53 and F1-Relaxed of 0.60 on the test set, ranking first among all participating teams under both evaluation criteria.</abstract>
    <identifier type="citekey">estuar-2026-team</identifier>
    <location>
        <url>https://aclanthology.org/2026.smm4h-1.6/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>28</start>
            <end>35</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Team Gazoo! at #SMM4H-HeaRD 2026: Zero-Training NER via Iterative LLM Prompt Self-Optimization for Opioid Impact Span Detection
%A Estuar, Diego
%Y Lopez-Garcia, Guillermo
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, United States
%@ 979-8-89176-432-3
%F estuar-2026-team
%X This paper describes the system submitted by Team Gazoo! for Task 7 of the #SMM4H-HeaRD 2026 shared task on detecting self-reported clinical and social impacts of nonmedical opioid use in social media text. We present a zero-training, prompt-only approach that uses a large language model (GPT-5.4) with structured few-shot prompting and autonomous, iterative rule optimization. Our system encodes a domain-specific entity ontology, three core decision rules, and 65 cognitively organized few-shot examples into a single prompt, with BIO constraint enforcement applied as post-processing. Crucially, the prompt itself is refined by the LLM: at each iteration the model analyzes its own errors and proposes targeted edits to its rules and examples. Through 18 such self-refinement cycles, our system achieved an F1-Strict of 0.53 and F1-Relaxed of 0.60 on the test set, ranking first among all participating teams under both evaluation criteria.
%U https://aclanthology.org/2026.smm4h-1.6/
%P 28-35

Markdown (Informal)

[Team Gazoo! at #SMM4H-HeaRD 2026: Zero-Training NER via Iterative LLM Prompt Self-Optimization for Opioid Impact Span Detection](https://aclanthology.org/2026.smm4h-1.6/) (Estuar, SMM4H 2026)

• Team Gazoo! at #SMM4H-HeaRD 2026: Zero-Training NER via Iterative LLM Prompt Self-Optimization for Opioid Impact Span Detection (Estuar, SMM4H 2026)

ACL

• Diego Estuar. 2026. Team Gazoo! at #SMM4H-HeaRD 2026: Zero-Training NER via Iterative LLM Prompt Self-Optimization for Opioid Impact Span Detection. In Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks, pages 28–35, San Diego, United States. Association for Computational Linguistics.