@inproceedings{boros-chivereanu-2026-racai-arguard,
title = "{RACAI} at {A}r{G}uard Shared Task: Exploring Self-Taught {LLM} Reasoners and Fine-Tuned Transformers Classifiers for {A}rabic Prompt Toxicity Detection",
author = "Boros, Tiberiu and
Chivereanu, Radu-Gabriel",
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.60/",
pages = "458--464",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents the systems we developed for ArGuard 2026 Task B, addressing Arabic prompt safety through binary safe/unsafe classification (B1) and fine-grained assignment of unsafe prompts to harm domains (B2). Our central strategy is cross-lingual data augmentation: we machine-translate a large English prompt-safety corpus into Arabic and reuse it across both subtasks. For B1 we fine-tune the Arabic-native ALLaM-7B on self-generated rationales using the granular labels from B2 as signal. We compare against label-only training; our submission ranks 2nd (macro $F_1{=}0.924$). The experiments show the augmentation drives accuracy and not the self-generated chain-of-thought. For B2 we fine-tune Arabic encoders (full and adapter tuning) with a two-stage ``warm' pipeline that first trains the encoder on the easier binary task, before specialising it to the seven domains; our submission ranks 5th (macro $F_1{=}0.762$)"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boros-chivereanu-2026-racai-arguard">
<titleInfo>
<title>RACAI at ArGuard Shared Task: Exploring Self-Taught LLM Reasoners and Fine-Tuned Transformers Classifiers for Arabic Prompt Toxicity Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tiberiu</namePart>
<namePart type="family">Boros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu-Gabriel</namePart>
<namePart type="family">Chivereanu</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>This paper presents the systems we developed for ArGuard 2026 Task B, addressing Arabic prompt safety through binary safe/unsafe classification (B1) and fine-grained assignment of unsafe prompts to harm domains (B2). Our central strategy is cross-lingual data augmentation: we machine-translate a large English prompt-safety corpus into Arabic and reuse it across both subtasks. For B1 we fine-tune the Arabic-native ALLaM-7B on self-generated rationales using the granular labels from B2 as signal. We compare against label-only training; our submission ranks 2nd (macro F₁=0.924). The experiments show the augmentation drives accuracy and not the self-generated chain-of-thought. For B2 we fine-tune Arabic encoders (full and adapter tuning) with a two-stage “warm’ pipeline that first trains the encoder on the easier binary task, before specialising it to the seven domains; our submission ranks 5th (macro F₁=0.762)</abstract>
<identifier type="citekey">boros-chivereanu-2026-racai-arguard</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.60/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>458</start>
<end>464</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RACAI at ArGuard Shared Task: Exploring Self-Taught LLM Reasoners and Fine-Tuned Transformers Classifiers for Arabic Prompt Toxicity Detection
%A Boros, Tiberiu
%A Chivereanu, Radu-Gabriel
%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 boros-chivereanu-2026-racai-arguard
%X This paper presents the systems we developed for ArGuard 2026 Task B, addressing Arabic prompt safety through binary safe/unsafe classification (B1) and fine-grained assignment of unsafe prompts to harm domains (B2). Our central strategy is cross-lingual data augmentation: we machine-translate a large English prompt-safety corpus into Arabic and reuse it across both subtasks. For B1 we fine-tune the Arabic-native ALLaM-7B on self-generated rationales using the granular labels from B2 as signal. We compare against label-only training; our submission ranks 2nd (macro F₁=0.924). The experiments show the augmentation drives accuracy and not the self-generated chain-of-thought. For B2 we fine-tune Arabic encoders (full and adapter tuning) with a two-stage “warm’ pipeline that first trains the encoder on the easier binary task, before specialising it to the seven domains; our submission ranks 5th (macro F₁=0.762)
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.60/
%P 458-464
Markdown (Informal)
[RACAI at ArGuard Shared Task: Exploring Self-Taught LLM Reasoners and Fine-Tuned Transformers Classifiers for Arabic Prompt Toxicity Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.60/) (Boros & Chivereanu, ArabicNLP 2026)
ACL