<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khamis-2026-gatech">
    <titleInfo>
        <title>GATech at AbjadMed: Bidirectional Encoders vs. Causal Decoders: Insights from 82-Class Arabic Medical Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ahmed</namePart>
        <namePart type="family">Khamis</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>This paper presents system description for Arabic medical text classification across 82 distinct categories. Our primary architecture utilizes a fine-tuned AraBERTv2 encoder enhanced with a hybrid pooling strategies, combining attention and mean representations, and multi-sample dropout for robust regularization. We systematically benchmark this approach against a suite of multilingual and Arabic-specific encoders, as well as several large-scale causal decoders, including zero-shot re-ranking via Llama 3.3 70B and feature extraction from Qwen 3B hidden states. Our findings demonstrate that specialized bidirectional encoders significantly outperform causal decoders in capturing the precise semantic boundaries required for fine-grained medical text classification. We show that causal decoders, optimized for next-token prediction, produce sequence-biased embeddings that are less effective for categorization compared to the global context captured by bidirectional attention. Despite significant class imbalance and label noise identified within the training data, our results highlight the superior semantic compression of fine-tuned encoders for specialized Arabic NLP tasks. Final performance metrics on the test set, including Accuracy and Macro-F1, are reported and discussed.</abstract>
    <identifier type="citekey">khamis-2026-gatech</identifier>
    <location>
        <url>https://aclanthology.org/2026.abjadnlp-1.13/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>105</start>
            <end>109</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T GATech at AbjadMed: Bidirectional Encoders vs. Causal Decoders: Insights from 82-Class Arabic Medical Classification
%A Khamis, Ahmed
%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 khamis-2026-gatech
%X This paper presents system description for Arabic medical text classification across 82 distinct categories. Our primary architecture utilizes a fine-tuned AraBERTv2 encoder enhanced with a hybrid pooling strategies, combining attention and mean representations, and multi-sample dropout for robust regularization. We systematically benchmark this approach against a suite of multilingual and Arabic-specific encoders, as well as several large-scale causal decoders, including zero-shot re-ranking via Llama 3.3 70B and feature extraction from Qwen 3B hidden states. Our findings demonstrate that specialized bidirectional encoders significantly outperform causal decoders in capturing the precise semantic boundaries required for fine-grained medical text classification. We show that causal decoders, optimized for next-token prediction, produce sequence-biased embeddings that are less effective for categorization compared to the global context captured by bidirectional attention. Despite significant class imbalance and label noise identified within the training data, our results highlight the superior semantic compression of fine-tuned encoders for specialized Arabic NLP tasks. Final performance metrics on the test set, including Accuracy and Macro-F1, are reported and discussed.
%U https://aclanthology.org/2026.abjadnlp-1.13/
%P 105-109

Markdown (Informal)

[GATech at AbjadMed: Bidirectional Encoders vs. Causal Decoders: Insights from 82-Class Arabic Medical Classification](https://aclanthology.org/2026.abjadnlp-1.13/) (Khamis, AbjadNLP 2026)

• GATech at AbjadMed: Bidirectional Encoders vs. Causal Decoders: Insights from 82-Class Arabic Medical Classification (Khamis, AbjadNLP 2026)

ACL

• Ahmed Khamis. 2026. GATech at AbjadMed: Bidirectional Encoders vs. Causal Decoders: Insights from 82-Class Arabic Medical Classification. In Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script, pages 105–109, Rabat, Morocco. Association for Computational Linguistics.