<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pachori-2026-bhramastra">
    <titleInfo>
        <title>Bhramastra at #SMM4H-HeaRD 2026: A Multi-Stage Hunter-Judge Pipeline using DSPy-Optimized LLMs for Multilingual ADE Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bhaarat</namePart>
        <namePart type="family">Pachori</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 submission by **Team Bhramastra** for the **#SMM4H-HeaRD 2026** Shared Task 1, focused on personal Adverse Drug Event (ADE) detection in multilingual social media. A decoupled architecture, **Hunter-Judge**, is proposed to handle extreme class imbalance and linguistic variance across seven languages, including a surprise zero-shot Farsi set. The system employs a fine-tuned multilingual mDeBERTa-v3 model as a high-recall filter (**Hunter**), followed by a Gemini-2.5-Flash model (**Judge**) optimized via the **DSPy** framework for precision-oriented agentic adjudication. By implementing a reasoning protocol grounded in clinical RAG evidence and universal ingredient mapping, the pipeline achieved the **highest average F1-score (0.6653)** among all teams. Strong zero-shot generalizability on Farsi (**F1: 0.5863**) was demonstrated, highlighting the effectiveness of medically-grounded adjudication in low-resource contexts.</abstract>
    <identifier type="citekey">pachori-2026-bhramastra</identifier>
    <location>
        <url>https://aclanthology.org/2026.smm4h-1.9/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>49</start>
            <end>55</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Bhramastra at #SMM4H-HeaRD 2026: A Multi-Stage Hunter-Judge Pipeline using DSPy-Optimized LLMs for Multilingual ADE Detection
%A Pachori, Bhaarat
%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 pachori-2026-bhramastra
%X This paper describes the submission by **Team Bhramastra** for the **#SMM4H-HeaRD 2026** Shared Task 1, focused on personal Adverse Drug Event (ADE) detection in multilingual social media. A decoupled architecture, **Hunter-Judge**, is proposed to handle extreme class imbalance and linguistic variance across seven languages, including a surprise zero-shot Farsi set. The system employs a fine-tuned multilingual mDeBERTa-v3 model as a high-recall filter (**Hunter**), followed by a Gemini-2.5-Flash model (**Judge**) optimized via the **DSPy** framework for precision-oriented agentic adjudication. By implementing a reasoning protocol grounded in clinical RAG evidence and universal ingredient mapping, the pipeline achieved the **highest average F1-score (0.6653)** among all teams. Strong zero-shot generalizability on Farsi (**F1: 0.5863**) was demonstrated, highlighting the effectiveness of medically-grounded adjudication in low-resource contexts.
%U https://aclanthology.org/2026.smm4h-1.9/
%P 49-55

Markdown (Informal)

[Bhramastra at #SMM4H-HeaRD 2026: A Multi-Stage Hunter-Judge Pipeline using DSPy-Optimized LLMs for Multilingual ADE Detection](https://aclanthology.org/2026.smm4h-1.9/) (Pachori, SMM4H 2026)

• Bhramastra at #SMM4H-HeaRD 2026: A Multi-Stage Hunter-Judge Pipeline using DSPy-Optimized LLMs for Multilingual ADE Detection (Pachori, SMM4H 2026)

ACL

• Bhaarat Pachori. 2026. Bhramastra at #SMM4H-HeaRD 2026: A Multi-Stage Hunter-Judge Pipeline using DSPy-Optimized LLMs for Multilingual ADE Detection. In Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks, pages 49–55, San Diego, United States. Association for Computational Linguistics.