Cover Image

FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fatehkia, Masoomali, Altinisik, Enes, Sencar, Husrev Taha
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PAM: Training Policy-Aligned Moderation Filters at Scale
by: Fatehkia, Masoomali, et al.
Published: (2025)

Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning
by: Ersoy, Asim, et al.
Published: (2025)

Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction
by: Altinisik, Enes, et al.
Published: (2026)

Explaining the role of Intrinsic Dimensionality in Adversarial Training
by: Altinisik, Enes, et al.
Published: (2024)

Fanar 2.0: Arabic Generative AI Stack
by: FANAR TEAM, et al.
Published: (2026)

Fanar: An Arabic-Centric Multimodal Generative AI Platform
by: Fanar Team, et al.
Published: (2025)

There Is More to Refusal in Large Language Models than a Single Direction
by: Joad, Faaiz, et al.
Published: (2026)

T-RAG: Lessons from the LLM Trenches
by: Fatehkia, Masoomali, et al.
Published: (2024)

Multimedia Forensics
by: Husrev Taha Sencar

CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications
by: Joshi, Raviraj, et al.
Published: (2025)

From Text to Actionable Intelligence: Automating STIX Entity and Relationship Extraction
by: Lekssays, Ahmed, et al.
Published: (2025)

Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA
by: Abbas, Ummar, et al.
Published: (2026)

PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
by: Kumar, Priyanshu, et al.
Published: (2025)

Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks
by: Bhatia, Gagan, et al.
Published: (2024)

Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset
by: Alwajih, Fakhraddin, et al.
Published: (2025)

STAND-Guard: A Small Task-Adaptive Content Moderation Model
by: Wang, Minjia, et al.
Published: (2024)

ExpGuard: LLM Content Moderation in Specialized Domains
by: Choi, Minseok, et al.
Published: (2026)

Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM
by: Alnumay, Yazeed, et al.
Published: (2025)

A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment
by: Elmadani, Khalid N., et al.
Published: (2025)

TSLFormer: A Lightweight Transformer Model for Turkish Sign Language Recognition Using Skeletal Landmarks
by: Ertürk, Kutay, et al.
Published: (2025)

BingoGuard: LLM Content Moderation Tools with Risk Levels
by: Yin, Fan, et al.
Published: (2025)

CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks
by: Qian, Zhaozhi, et al.
Published: (2024)

Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic
by: Alwajih, Fakhraddin, et al.
Published: (2024)

The Landscape of Arabic Large Language Models (ALLMs): A New Era for Arabic Language Technology
by: Al-Khalifa, Shahad, et al.
Published: (2025)

On Calibration of LLM-based Guard Models for Reliable Content Moderation
by: Liu, Hongfu, et al.
Published: (2024)

LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models
by: Elesedy, Hayder, et al.
Published: (2024)

TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text
by: Lekssays, Ahmed, et al.
Published: (2025)

UbuntuGuard: A Culturally-Grounded Policy Benchmark for Equitable AI Safety in African Languages
by: Abdullahi, Tassallah, et al.
Published: (2026)

Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation
by: Wróbel, Krzysztof, et al.
Published: (2026)

Guidelines for Fine-grained Sentence-level Arabic Readability Annotation
by: Habash, Nizar, et al.
Published: (2024)

ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic
by: Koto, Fajri, et al.
Published: (2024)

Socio-Culturally Aware Evaluation Framework for LLM-Based Content Moderation
by: Kumar, Shanu, et al.
Published: (2024)

SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia
by: Tasawong, Panuthep, et al.
Published: (2026)

MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention
by: Jha, Prince, et al.
Published: (2024)

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
by: Han, Seungju, et al.
Published: (2024)

DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models
by: Altakrori, Malik H., et al.
Published: (2025)

ArabicNumBench: Evaluating Arabic Number Reading in Large Language Models
by: Alhumud, Anas, et al.
Published: (2026)

Arabic Large Language Models for Medical Text Generation
by: Allam, Abdulrahman, et al.
Published: (2025)

On the importance of Data Scale in Pretraining Arabic Language Models
by: Ghaddar, Abbas, et al.
Published: (2024)

AlcLaM: Arabic Dialectal Language Model
by: Ahmed, Murtadha, et al.
Published: (2024)