@inproceedings{abdo-2026-salahabdo,
title = "{S}alah{A}bdo at Daleel 2026: Routing Each Label to {LLM} Votes, a Fine-Tuned Encoder, or Sequence Structure",
author = "Abdo, Salah",
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.164/",
pages = "1310--1322",
ISBN = "979-8-89176-497-2",
abstract = "We describe the SalahAbdo closed-track systems for both Daleel 2026 subtasks: deciding which argumentative-unit types appear in an Arabic paragraph (Task 1) and locating their exact spans (Task 2), in editorials and debates. No single method was best for all six argumentative-unit types, so our Task 1 system routes each type to the method that measured best for it: assumption (AS), testimony (TE), and statistics (ST) are detected by sampling a gemma-4-31b classifier five times and firing when enough samples agree; anecdote (AN) and other (OT) by a fine-tuned CAMeLBERT classifier; and the lowest-agreement type, common ground (CO), by ranking paragraphs and firing a fixed count. A final verifier shows the LLM examples of true and false ST paragraphs and removes likely false positives. Task 2 first extracts spans as verbatim LLM quotes, then re-labels them by blending encoder probabilities with label-sequence statistics under Viterbi decoding, with zero additional LLM calls. Every design change had to clear an adoption bar set before its result was read: 29 recorded decisions produced six adoptions, and composition arithmetic over already-scored legs predicted two development scores digit-for-digit. Development scores are 0.7089 macro-F1 (Task 1) and 0.7247 span F1 (Task 2); the pinned recipes scored 0.6499 and 0.7055 on test, and our final official submissions scored 0.712 and 0.7316: first of ten and fifth of eight closed-track teams (Section 6 discloses the evaluation-phase protocol). Residual errors track the scheme{'}s measured human agreement (kappa as low as 0.114): types whose definitions a model can check against the text improved under LLM verification, while types defined by annotation convention resisted every prompting attack and were learned only from supervision and sequence structure."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdo-2026-salahabdo">
<titleInfo>
<title>SalahAbdo at Daleel 2026: Routing Each Label to LLM Votes, a Fine-Tuned Encoder, or Sequence Structure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Salah</namePart>
<namePart type="family">Abdo</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 SalahAbdo closed-track systems for both Daleel 2026 subtasks: deciding which argumentative-unit types appear in an Arabic paragraph (Task 1) and locating their exact spans (Task 2), in editorials and debates. No single method was best for all six argumentative-unit types, so our Task 1 system routes each type to the method that measured best for it: assumption (AS), testimony (TE), and statistics (ST) are detected by sampling a gemma-4-31b classifier five times and firing when enough samples agree; anecdote (AN) and other (OT) by a fine-tuned CAMeLBERT classifier; and the lowest-agreement type, common ground (CO), by ranking paragraphs and firing a fixed count. A final verifier shows the LLM examples of true and false ST paragraphs and removes likely false positives. Task 2 first extracts spans as verbatim LLM quotes, then re-labels them by blending encoder probabilities with label-sequence statistics under Viterbi decoding, with zero additional LLM calls. Every design change had to clear an adoption bar set before its result was read: 29 recorded decisions produced six adoptions, and composition arithmetic over already-scored legs predicted two development scores digit-for-digit. Development scores are 0.7089 macro-F1 (Task 1) and 0.7247 span F1 (Task 2); the pinned recipes scored 0.6499 and 0.7055 on test, and our final official submissions scored 0.712 and 0.7316: first of ten and fifth of eight closed-track teams (Section 6 discloses the evaluation-phase protocol). Residual errors track the scheme’s measured human agreement (kappa as low as 0.114): types whose definitions a model can check against the text improved under LLM verification, while types defined by annotation convention resisted every prompting attack and were learned only from supervision and sequence structure.</abstract>
<identifier type="citekey">abdo-2026-salahabdo</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.164/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1310</start>
<end>1322</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SalahAbdo at Daleel 2026: Routing Each Label to LLM Votes, a Fine-Tuned Encoder, or Sequence Structure
%A Abdo, Salah
%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 abdo-2026-salahabdo
%X We describe the SalahAbdo closed-track systems for both Daleel 2026 subtasks: deciding which argumentative-unit types appear in an Arabic paragraph (Task 1) and locating their exact spans (Task 2), in editorials and debates. No single method was best for all six argumentative-unit types, so our Task 1 system routes each type to the method that measured best for it: assumption (AS), testimony (TE), and statistics (ST) are detected by sampling a gemma-4-31b classifier five times and firing when enough samples agree; anecdote (AN) and other (OT) by a fine-tuned CAMeLBERT classifier; and the lowest-agreement type, common ground (CO), by ranking paragraphs and firing a fixed count. A final verifier shows the LLM examples of true and false ST paragraphs and removes likely false positives. Task 2 first extracts spans as verbatim LLM quotes, then re-labels them by blending encoder probabilities with label-sequence statistics under Viterbi decoding, with zero additional LLM calls. Every design change had to clear an adoption bar set before its result was read: 29 recorded decisions produced six adoptions, and composition arithmetic over already-scored legs predicted two development scores digit-for-digit. Development scores are 0.7089 macro-F1 (Task 1) and 0.7247 span F1 (Task 2); the pinned recipes scored 0.6499 and 0.7055 on test, and our final official submissions scored 0.712 and 0.7316: first of ten and fifth of eight closed-track teams (Section 6 discloses the evaluation-phase protocol). Residual errors track the scheme’s measured human agreement (kappa as low as 0.114): types whose definitions a model can check against the text improved under LLM verification, while types defined by annotation convention resisted every prompting attack and were learned only from supervision and sequence structure.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.164/
%P 1310-1322
Markdown (Informal)
[SalahAbdo at Daleel 2026: Routing Each Label to LLM Votes, a Fine-Tuned Encoder, or Sequence Structure](https://aclanthology.org/2026.arabicnlp-sharedtasks.164/) (Abdo, ArabicNLP 2026)
ACL