19 citations · 75 across the 22 of their papers we have counts for
28 papers
From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data
Husrev Taha Sencar, Rezart Beka, Danish Naeem +6
Aligning language models with a specified normative framework requires translating abstract principles into concrete examples and preference signals from which models can learn. We…
Latent Mechanisms of Language Control in Multilingual Language Models
Ryo Mitsuhashi, Sabri Boughorbel, Majd Hawasly
Multilingual large language models can exhibit unintended code-switching -- unnecessarily alternating between languages during generation. We present a comparative study of three m…
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
Raman Saparkhan, Majd Hawasly, Md Rizwan Parvez +1
Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computati…
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…
Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA
Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh +7
Large language models (LLMs) can answer religious knowledge queries fluently, yet they often hallucinate and misattribute sources, which is especially consequential in Islamic sett…
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 direction, enabling steering and abliteration. We show that this account is incomplete: across diver…
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…
SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?
Azmine Toushik Wasi, Wahid Faisal, Abdur Rahman +12
Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs). Prior work largely relied on syntheti…
Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing
Sabri Boughorbel, Fahim Dalvi, Nadir Durrani +1
As fine-tuning becomes the dominant paradigm for improving large language models (LLMs), understanding what changes during this process is increasingly important. Traditional bench…
PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture
Fakhraddin Alwajih, Abdellah El Mekki, Hamdy Mubarak +3
Large Language Models (LLMs) inherently reflect the vast data distributions they encounter during their pre-training phase. As this data is predominantly sourced from the web, ther…
Fanar: An Arabic-Centric Multimodal Generative AI Platform
Fanar Team, Ummar Abbas, Mohammad Shahmeer Ahmad +39
We present Fanar, a platform for Arabic-centric multimodal generative AI systems, that supports language, speech and image generation tasks. At the heart of Fanar are Fanar Star an…
Exploring Alignment in Shared Cross-lingual Spaces
Basel Mousi, Nadir Durrani, Fahim Dalvi +2
Despite their remarkable ability to capture linguistic nuances across diverse languages, questions persist regarding the degree of alignment between languages in multilingual embed…
Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis
Sabri Boughorbel, MD Rizwan Parvez, Majd Hawasly
Training LLMs for low-resource languages usually utilizes data augmentation from English using machine translation (MT). This, however, brings a number of challenges to LLM trainin…
Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic
Sabri Boughorbel, Majd Hawasly
While significant progress has been made in benchmarking Large Language Models (LLMs) across various tasks, there is a lack of comprehensive evaluation of their abilities in respon…
Scaling up Discovery of Latent Concepts in Deep NLP Models
Majd Hawasly, Fahim Dalvi, Nadir Durrani
Despite the revolution caused by deep NLP models, they remain black boxes, necessitating research to understand their decision-making processes. A recent work by Dalvi et al. (2022…
LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking
Fahim Dalvi, Maram Hasanain, Sabri Boughorbel +10
The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several…
LAraBench: Benchmarking Arabic AI with Large Language Models
Ahmed Abdelali, Hamdy Mubarak, Shammur Absar Chowdhury +13
Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific b…
DiPA: Probabilistic Multi-Modal Interactive Prediction for Autonomous Driving
Anthony Knittel, Majd Hawasly, Stefano V. Albrecht +2
Accurate prediction is important for operating an autonomous vehicle in interactive scenarios. Prediction must be fast, to support multiple requests from a planner exploring a rang…
Perspectives on the System-level Design of a Safe Autonomous Driving Stack
Majd Hawasly, Jonathan Sadeghi, Morris Antonello +3
Achieving safe and robust autonomy is the key bottleneck on the path towards broader adoption of autonomous vehicles technology. This motivates going beyond extrinsic metrics such…
Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?
Aravinda Ramakrishnan Srinivasan, Yi-Shin Lin, Morris Antonello +9
Autonomous vehicles use a variety of sensors and machine-learned models to predict the behavior of surrounding road users. Most of the machine-learned models in the literature focu…
PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving
Henry Pulver, Francisco Eiras, Ludovico Carozza +3
Achieving a proper balance between planning quality, safety and efficiency is a major challenge for autonomous driving. Optimisation-based motion planners are capable of producing…
A Two-Stage Optimization-based Motion Planner for Safe Urban Driving
Francisco Eiras, Majd Hawasly, Stefano V. Albrecht +1
Recent road trials have shown that guaranteeing the safety of driving decisions is essential for the wider adoption of autonomous vehicle technology. One promising direction is to…
PaRoT: A Practical Framework for Robust Deep Neural Network Training
Edward Ayers, Francisco Eiras, Majd Hawasly +1
Deep Neural Networks (DNNs) are finding important applications in safety-critical systems such as Autonomous Vehicles (AVs), where perceiving the environment correctly and robustly…
FPR -- Fast Path Risk Algorithm to Evaluate Collision Probability
Andrew Blake, Alejandro Bordallo, Kamen Brestnichki +4
As mobile robots and autonomous vehicles become increasingly prevalent in human-centred environments, there is a need to control the risk of collision. Perceptual modules, for exam…