10 papers
Fanar 2.0: Arabic Generative AI Stack
FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad +34
We present Fanar 2.0, the second generation of Qatar's Arabic-centric Generative AI platform. Sovereignty is a first-class design principle: every component, from data pipelines to…
There Is More to Refusal in Large Language Models than a Single Direction
Faaiz Joad, Majd Hawasly, Sabri Boughorbel +2
Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and ablation. We show that this account is i…
Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction
Enes Altinisik, Masoomali Fatehkia, Fatih Deniz +4
Factual hallucination remains a central challenge for large language models (LLMs). Existing mitigation approaches primarily rely on either external post-hoc verification or mappin…
PAM: Training Policy-Aligned Moderation Filters at Scale
Masoomali Fatehkia, Enes Altinisik, Mohamed Osman +1
Large language models (LLMs) remain vulnerable to misalignment and jailbreaks, making external safeguards like moderation filters essential, yet existing filters often focus narrow…
FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models
Masoomali Fatehkia, Enes Altinisik, Husrev Taha Sencar
Content moderation filters are a critical safeguard against alignment failures in language models. Yet most existing filters focus narrowly on general safety and overlook cultural…
Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning
Asim Ersoy, Enes Altinisik, Husrev Taha Sencar +1
Tool calling is a critical capability that allows Large Language Models (LLMs) to interact with external systems, significantly expanding their utility. However, research and resou…