<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khallouf-2026-baellouf">
    <titleInfo>
        <title>baellouf at AbjadMed: Efficient Fine-tuning with All-Linear LoRA for Arabic Medical QA Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abdallah</namePart>
        <namePart type="family">Khallouf</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We describe our system for the AbjadMed shared task on Arabic medical text classification at AbjadNLP 2026. Our approach combines efficient fine-tuning of Qwen3-8B using QLoRA with a Dice+CrossEntropy hybrid loss designed for Macro F1 optimization. Taking inspiration from recent research on optimal LoRA configurations, we apply low-rank adapters to all linear layers of the model rather than attention layers only, which we validate improves performance by 4.0 points. We also explore data augmentation through machine translation of external medical QA data, though this did not improve generalization. Our best submission achieves a Macro F1 score of 0.4441 on the test set.</abstract>
    <identifier type="citekey">khallouf-2026-baellouf</identifier>
    <location>
        <url>https://aclanthology.org/2026.abjadnlp-1.17/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>124</start>
            <end>126</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T baellouf at AbjadMed: Efficient Fine-tuning with All-Linear LoRA for Arabic Medical QA Classification
%A Khallouf, Abdallah
%S Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F khallouf-2026-baellouf
%X We describe our system for the AbjadMed shared task on Arabic medical text classification at AbjadNLP 2026. Our approach combines efficient fine-tuning of Qwen3-8B using QLoRA with a Dice+CrossEntropy hybrid loss designed for Macro F1 optimization. Taking inspiration from recent research on optimal LoRA configurations, we apply low-rank adapters to all linear layers of the model rather than attention layers only, which we validate improves performance by 4.0 points. We also explore data augmentation through machine translation of external medical QA data, though this did not improve generalization. Our best submission achieves a Macro F1 score of 0.4441 on the test set.
%U https://aclanthology.org/2026.abjadnlp-1.17/
%P 124-126

Markdown (Informal)

[baellouf at AbjadMed: Efficient Fine-tuning with All-Linear LoRA for Arabic Medical QA Classification](https://aclanthology.org/2026.abjadnlp-1.17/) (Khallouf, AbjadNLP 2026)

• baellouf at AbjadMed: Efficient Fine-tuning with All-Linear LoRA for Arabic Medical QA Classification (Khallouf, AbjadNLP 2026)

ACL

• Abdallah Khallouf. 2026. baellouf at AbjadMed: Efficient Fine-tuning with All-Linear LoRA for Arabic Medical QA Classification. In Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script, pages 124–126, Rabat, Morocco. Association for Computational Linguistics.