@inproceedings{alshehri-etal-2026-durham,
title = "{D}urham-Jazan at Daleel 2026: Domain-Routed Ensembles, {LLM} Augmentation, and the Limits of Decision-Rule Tuning for {A}rabic Argument Mining",
author = "Alshehri, Amal Saad and
Bencomo, Nelly and
Babiker, Housam and
Atapour-Abarghouei, Amir",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.166/",
pages = "1328--1343",
ISBN = "979-8-89176-497-2",
abstract = "We describe the Durham-Jazan submissions to the Daleel 2026 shared task on Arabic argumentative discourse mining, which comprises multi-label paragraph classification (Task 1) and argumentative span detection (Task 2), each with a Closed and an Open track. Our Task 2 Closed system routes the Modern Standard Arabic editorials to CAMeLBERT and the noisier debate transcripts to MARBERTv2. The Open system blends the two families at character level and adds synthetic training data from a large language model for rare-class generalisation, generated by a segment-concatenation recipe that makes span offsets exact by construction. The Task 1 systems add back-translation, targeted augmentation of the rare classes, and a QLoRA-tuned Qwen3-32B for the editorials. Everything else trains on one 16 GB consumer GPU. Our official test scores are 0.729 and 0.736 overlap-F1 on Task 2 and 0.657 and 0.669 macro-F1 on Task 1 (Closed and Open). We placed first of two on Task 1 Open, first of one on Task 2 Open, fifth of ten on Task 1 Closed, and sixth of eight on Task 2 Closed. Our central finding concerns our own systems on this data. Recalibrating per-class thresholds on validation outputs overfits them. Under a controlled protocol the held-out effect is negative at every tuning-set size we tested, while the apparent in-sample gain shrinks as the tuning set grows. An audit of eighteen interventions from our campaign is consistent with this, though observational. A size-matched study links the editorial deficit that every team showed to the genre composition of the training data. We release our code and synthetic data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alshehri-etal-2026-durham">
<titleInfo>
<title>Durham-Jazan at Daleel 2026: Domain-Routed Ensembles, LLM Augmentation, and the Limits of Decision-Rule Tuning for Arabic Argument Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="given">Saad</namePart>
<namePart type="family">Alshehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelly</namePart>
<namePart type="family">Bencomo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Housam</namePart>
<namePart type="family">Babiker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Atapour-Abarghouei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>We describe the Durham-Jazan submissions to the Daleel 2026 shared task on Arabic argumentative discourse mining, which comprises multi-label paragraph classification (Task 1) and argumentative span detection (Task 2), each with a Closed and an Open track. Our Task 2 Closed system routes the Modern Standard Arabic editorials to CAMeLBERT and the noisier debate transcripts to MARBERTv2. The Open system blends the two families at character level and adds synthetic training data from a large language model for rare-class generalisation, generated by a segment-concatenation recipe that makes span offsets exact by construction. The Task 1 systems add back-translation, targeted augmentation of the rare classes, and a QLoRA-tuned Qwen3-32B for the editorials. Everything else trains on one 16 GB consumer GPU. Our official test scores are 0.729 and 0.736 overlap-F1 on Task 2 and 0.657 and 0.669 macro-F1 on Task 1 (Closed and Open). We placed first of two on Task 1 Open, first of one on Task 2 Open, fifth of ten on Task 1 Closed, and sixth of eight on Task 2 Closed. Our central finding concerns our own systems on this data. Recalibrating per-class thresholds on validation outputs overfits them. Under a controlled protocol the held-out effect is negative at every tuning-set size we tested, while the apparent in-sample gain shrinks as the tuning set grows. An audit of eighteen interventions from our campaign is consistent with this, though observational. A size-matched study links the editorial deficit that every team showed to the genre composition of the training data. We release our code and synthetic data.</abstract>
<identifier type="citekey">alshehri-etal-2026-durham</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.166/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1328</start>
<end>1343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Durham-Jazan at Daleel 2026: Domain-Routed Ensembles, LLM Augmentation, and the Limits of Decision-Rule Tuning for Arabic Argument Mining
%A Alshehri, Amal Saad
%A Bencomo, Nelly
%A Babiker, Housam
%A Atapour-Abarghouei, Amir
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F alshehri-etal-2026-durham
%X We describe the Durham-Jazan submissions to the Daleel 2026 shared task on Arabic argumentative discourse mining, which comprises multi-label paragraph classification (Task 1) and argumentative span detection (Task 2), each with a Closed and an Open track. Our Task 2 Closed system routes the Modern Standard Arabic editorials to CAMeLBERT and the noisier debate transcripts to MARBERTv2. The Open system blends the two families at character level and adds synthetic training data from a large language model for rare-class generalisation, generated by a segment-concatenation recipe that makes span offsets exact by construction. The Task 1 systems add back-translation, targeted augmentation of the rare classes, and a QLoRA-tuned Qwen3-32B for the editorials. Everything else trains on one 16 GB consumer GPU. Our official test scores are 0.729 and 0.736 overlap-F1 on Task 2 and 0.657 and 0.669 macro-F1 on Task 1 (Closed and Open). We placed first of two on Task 1 Open, first of one on Task 2 Open, fifth of ten on Task 1 Closed, and sixth of eight on Task 2 Closed. Our central finding concerns our own systems on this data. Recalibrating per-class thresholds on validation outputs overfits them. Under a controlled protocol the held-out effect is negative at every tuning-set size we tested, while the apparent in-sample gain shrinks as the tuning set grows. An audit of eighteen interventions from our campaign is consistent with this, though observational. A size-matched study links the editorial deficit that every team showed to the genre composition of the training data. We release our code and synthetic data.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.166/
%P 1328-1343
Markdown (Informal)
[Durham-Jazan at Daleel 2026: Domain-Routed Ensembles, LLM Augmentation, and the Limits of Decision-Rule Tuning for Arabic Argument Mining](https://aclanthology.org/2026.arabicnlp-sharedtasks.166/) (Alshehri et al., ArabicNLP 2026)
ACL