@inproceedings{bilianos-2026-dbilianos,
title = "dbilianos at {A}r{G}uard Shared Tasks: When Does Translation Help in {A}rabic Harmful Prompt Detection?",
author = "Bilianos, Dimitris",
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.40/",
pages = "326--331",
ISBN = "979-8-89176-497-2",
abstract = "This paper describes the participation of the dbilianos team in the ArGuard 2026 Shared Task on harmful prompt detection for Arabic LLM safety evaluation. We participated in both subtasks: binary safe/unsafe classification (Task B1) and granular harm category classification (Task B2). Our approach systematically tested a central hypothesis: whether translating Arabic prompts into English improves classification performance. We experimented with multiple pipelines, including classical machine learning with TF-IDF features, zero-shot and few-shot prompting with DeepSeek-V4, and hybrid approaches. Our results reveal a divergence across subtasks. For binary classification, DeepSeek zero-shot on English translations achieved 0.89 macro-F1, securing 4th place in this subtask, and confirming that LLM-based prompting is highly effective for coarse-grained safety decisions. For granular classification, however, the best performance came from training a Support Vector Machine directly on original Arabic text using TF-IDF features, which achieved 0.61 macro-F1, placing the team 16th in this subtask. This outperformed our translation-based strategies, suggesting that fine-grained harm categorization is highly sensitive to linguistic and cultural nuance that is lost or distorted during translation. The translation hypothesis was only partially supported locally, and ultimately reversed on the final test set for both subtasks. We discuss implications for cross-lingual safety evaluation and highlight the limitations of translation-based pipelines for tasks requiring subtle intent interpretation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bilianos-2026-dbilianos">
<titleInfo>
<title>dbilianos at ArGuard Shared Tasks: When Does Translation Help in Arabic Harmful Prompt Detection?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitris</namePart>
<namePart type="family">Bilianos</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 describes the participation of the dbilianos team in the ArGuard 2026 Shared Task on harmful prompt detection for Arabic LLM safety evaluation. We participated in both subtasks: binary safe/unsafe classification (Task B1) and granular harm category classification (Task B2). Our approach systematically tested a central hypothesis: whether translating Arabic prompts into English improves classification performance. We experimented with multiple pipelines, including classical machine learning with TF-IDF features, zero-shot and few-shot prompting with DeepSeek-V4, and hybrid approaches. Our results reveal a divergence across subtasks. For binary classification, DeepSeek zero-shot on English translations achieved 0.89 macro-F1, securing 4th place in this subtask, and confirming that LLM-based prompting is highly effective for coarse-grained safety decisions. For granular classification, however, the best performance came from training a Support Vector Machine directly on original Arabic text using TF-IDF features, which achieved 0.61 macro-F1, placing the team 16th in this subtask. This outperformed our translation-based strategies, suggesting that fine-grained harm categorization is highly sensitive to linguistic and cultural nuance that is lost or distorted during translation. The translation hypothesis was only partially supported locally, and ultimately reversed on the final test set for both subtasks. We discuss implications for cross-lingual safety evaluation and highlight the limitations of translation-based pipelines for tasks requiring subtle intent interpretation.</abstract>
<identifier type="citekey">bilianos-2026-dbilianos</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.40/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>326</start>
<end>331</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T dbilianos at ArGuard Shared Tasks: When Does Translation Help in Arabic Harmful Prompt Detection?
%A Bilianos, Dimitris
%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 bilianos-2026-dbilianos
%X This paper describes the participation of the dbilianos team in the ArGuard 2026 Shared Task on harmful prompt detection for Arabic LLM safety evaluation. We participated in both subtasks: binary safe/unsafe classification (Task B1) and granular harm category classification (Task B2). Our approach systematically tested a central hypothesis: whether translating Arabic prompts into English improves classification performance. We experimented with multiple pipelines, including classical machine learning with TF-IDF features, zero-shot and few-shot prompting with DeepSeek-V4, and hybrid approaches. Our results reveal a divergence across subtasks. For binary classification, DeepSeek zero-shot on English translations achieved 0.89 macro-F1, securing 4th place in this subtask, and confirming that LLM-based prompting is highly effective for coarse-grained safety decisions. For granular classification, however, the best performance came from training a Support Vector Machine directly on original Arabic text using TF-IDF features, which achieved 0.61 macro-F1, placing the team 16th in this subtask. This outperformed our translation-based strategies, suggesting that fine-grained harm categorization is highly sensitive to linguistic and cultural nuance that is lost or distorted during translation. The translation hypothesis was only partially supported locally, and ultimately reversed on the final test set for both subtasks. We discuss implications for cross-lingual safety evaluation and highlight the limitations of translation-based pipelines for tasks requiring subtle intent interpretation.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.40/
%P 326-331
Markdown (Informal)
[dbilianos at ArGuard Shared Tasks: When Does Translation Help in Arabic Harmful Prompt Detection?](https://aclanthology.org/2026.arabicnlp-sharedtasks.40/) (Bilianos, ArabicNLP 2026)
ACL