@inproceedings{babu-2026-saigum,
title = "Saigum at {S}tance{E}val-2026: Evaluating {LLM}-ensemble models and Retrieval Augmented Classification for {A}rabic Stance Detection",
author = "Babu, Sairam Narendra",
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.75/",
pages = "589--601",
ISBN = "979-8-89176-497-2",
abstract = "Arabic stance depends on quotation, sarcasm, negation, hashtags, and target scope, which surface polarity may miss. For StanceEval-2026, we study Codex and Gemini prompting through two submission systems: a replicated contextual Codex predictor and a gated judge that retrieves labeled examples using seven AI-generated discourse cues. On 619 Dev examples, cue retrieval changes Favg2 from 0.8580 to 0.8613 for GPT-5.6-luna, 0.8767 to 0.8844 for Gemini 3.5 Flash, and 0.8646 to 0.8554 for Flash-Lite. Random and semantic controls show no consistent retrieval advantage. On the 352-row hidden set, the best retained Codex member scores 0.8685 Favg2 and currently ranks fourth, while gated retrieval scores 0.8604. Codex and OPUS-MT translation pipelines score 0.7848 and 0.7304, and a synthetic-data classifier scores 0.7334. These results support replication and retrieval as auditable system components, not as general performance gains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="babu-2026-saigum">
<titleInfo>
<title>Saigum at StanceEval-2026: Evaluating LLM-ensemble models and Retrieval Augmented Classification for Arabic Stance Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sairam</namePart>
<namePart type="given">Narendra</namePart>
<namePart type="family">Babu</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>Arabic stance depends on quotation, sarcasm, negation, hashtags, and target scope, which surface polarity may miss. For StanceEval-2026, we study Codex and Gemini prompting through two submission systems: a replicated contextual Codex predictor and a gated judge that retrieves labeled examples using seven AI-generated discourse cues. On 619 Dev examples, cue retrieval changes Favg2 from 0.8580 to 0.8613 for GPT-5.6-luna, 0.8767 to 0.8844 for Gemini 3.5 Flash, and 0.8646 to 0.8554 for Flash-Lite. Random and semantic controls show no consistent retrieval advantage. On the 352-row hidden set, the best retained Codex member scores 0.8685 Favg2 and currently ranks fourth, while gated retrieval scores 0.8604. Codex and OPUS-MT translation pipelines score 0.7848 and 0.7304, and a synthetic-data classifier scores 0.7334. These results support replication and retrieval as auditable system components, not as general performance gains.</abstract>
<identifier type="citekey">babu-2026-saigum</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.75/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>589</start>
<end>601</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Saigum at StanceEval-2026: Evaluating LLM-ensemble models and Retrieval Augmented Classification for Arabic Stance Detection
%A Babu, Sairam Narendra
%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 babu-2026-saigum
%X Arabic stance depends on quotation, sarcasm, negation, hashtags, and target scope, which surface polarity may miss. For StanceEval-2026, we study Codex and Gemini prompting through two submission systems: a replicated contextual Codex predictor and a gated judge that retrieves labeled examples using seven AI-generated discourse cues. On 619 Dev examples, cue retrieval changes Favg2 from 0.8580 to 0.8613 for GPT-5.6-luna, 0.8767 to 0.8844 for Gemini 3.5 Flash, and 0.8646 to 0.8554 for Flash-Lite. Random and semantic controls show no consistent retrieval advantage. On the 352-row hidden set, the best retained Codex member scores 0.8685 Favg2 and currently ranks fourth, while gated retrieval scores 0.8604. Codex and OPUS-MT translation pipelines score 0.7848 and 0.7304, and a synthetic-data classifier scores 0.7334. These results support replication and retrieval as auditable system components, not as general performance gains.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.75/
%P 589-601
Markdown (Informal)
[Saigum at StanceEval-2026: Evaluating LLM-ensemble models and Retrieval Augmented Classification for Arabic Stance Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.75/) (Babu, ArabicNLP 2026)
ACL