@inproceedings{srivastava-2026-lattice,
title = "Lattice {AI} at {A}r{G}uard Shared Tasks: Encoder Ensembles and a Re-Annotated Test Slice in {A}rabic Harmful-Prompt Detection",
author = "Srivastava, Rahul",
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.45/",
pages = "363--370",
ISBN = "979-8-89176-497-2",
abstract = "We describe our system for the ArGuard 2026 shared task (Task B), harmful-prompt detection for Arabic, with subtasks B1 (binary safe versus unsafe) and B2 (seven-way harm-domain classification), both scored by macro-F1. Our system pairs a Unicode-normalization front-end with an ensemble of fine-tuned Arabic encoders, treats B2 as topic-domain classification over all prompts, and adds a retrieval-augmented resolver for the confusable interpersonal classes; it reaches development macro-F1 0.907 (B2) and 0.950 (B1), and on the blind test B1 0.9839 (1st, tied) and B2 0.7875 (2nd). Our main contribution explains the large B2 development-to-test gap. One fifth of the B2 test is a ``novel'' slice: AraSafe prompts re-annotated into the seven ArGuard domains under a fixed cross-taxonomy mapping that the organizers confirmed. Because that mapping does not preserve the training convention and is recorded in no data available during the task, no system can infer it, and the competitive B2 field compresses onto a blind 0.68-0.79 band, far below the {\textasciitilde}0.90 reachable in-distribution. On the familiar slice we score macro-F1 0.908, matching development; we argue this is the honest measure of the system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="srivastava-2026-lattice">
<titleInfo>
<title>Lattice AI at ArGuard Shared Tasks: Encoder Ensembles and a Re-Annotated Test Slice in Arabic Harmful-Prompt Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Srivastava</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 our system for the ArGuard 2026 shared task (Task B), harmful-prompt detection for Arabic, with subtasks B1 (binary safe versus unsafe) and B2 (seven-way harm-domain classification), both scored by macro-F1. Our system pairs a Unicode-normalization front-end with an ensemble of fine-tuned Arabic encoders, treats B2 as topic-domain classification over all prompts, and adds a retrieval-augmented resolver for the confusable interpersonal classes; it reaches development macro-F1 0.907 (B2) and 0.950 (B1), and on the blind test B1 0.9839 (1st, tied) and B2 0.7875 (2nd). Our main contribution explains the large B2 development-to-test gap. One fifth of the B2 test is a “novel” slice: AraSafe prompts re-annotated into the seven ArGuard domains under a fixed cross-taxonomy mapping that the organizers confirmed. Because that mapping does not preserve the training convention and is recorded in no data available during the task, no system can infer it, and the competitive B2 field compresses onto a blind 0.68-0.79 band, far below the ~0.90 reachable in-distribution. On the familiar slice we score macro-F1 0.908, matching development; we argue this is the honest measure of the system.</abstract>
<identifier type="citekey">srivastava-2026-lattice</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.45/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>363</start>
<end>370</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lattice AI at ArGuard Shared Tasks: Encoder Ensembles and a Re-Annotated Test Slice in Arabic Harmful-Prompt Detection
%A Srivastava, Rahul
%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 srivastava-2026-lattice
%X We describe our system for the ArGuard 2026 shared task (Task B), harmful-prompt detection for Arabic, with subtasks B1 (binary safe versus unsafe) and B2 (seven-way harm-domain classification), both scored by macro-F1. Our system pairs a Unicode-normalization front-end with an ensemble of fine-tuned Arabic encoders, treats B2 as topic-domain classification over all prompts, and adds a retrieval-augmented resolver for the confusable interpersonal classes; it reaches development macro-F1 0.907 (B2) and 0.950 (B1), and on the blind test B1 0.9839 (1st, tied) and B2 0.7875 (2nd). Our main contribution explains the large B2 development-to-test gap. One fifth of the B2 test is a “novel” slice: AraSafe prompts re-annotated into the seven ArGuard domains under a fixed cross-taxonomy mapping that the organizers confirmed. Because that mapping does not preserve the training convention and is recorded in no data available during the task, no system can infer it, and the competitive B2 field compresses onto a blind 0.68-0.79 band, far below the ~0.90 reachable in-distribution. On the familiar slice we score macro-F1 0.908, matching development; we argue this is the honest measure of the system.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.45/
%P 363-370
Markdown (Informal)
[Lattice AI at ArGuard Shared Tasks: Encoder Ensembles and a Re-Annotated Test Slice in Arabic Harmful-Prompt Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.45/) (Srivastava, ArabicNLP 2026)
ACL