← Search

Ahmed Oumar El-Shangiti

4 accepted papers

2025

Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs

ACL 2025long

As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce PALM, a year-long community-driven project covering all 22 Arab countries. The dataset contains instruction–response pairs in both Modern Sta…

2025

The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces

NAACL 2025short

This paper investigates whether large language models (LLMs) utilize numerical attributes encoded in a low-dimensional subspace of theembedding space when answering questions involving numeric comparisons, e.g., Was Cristiano born before Messi? We first identified,using partial least squares regress…

Cited by 1SourcePDFScholar
2024

Casablanca: Data and Models for Multidialectal Arabic Speech Recognition

EMNLP 2024main

In spite of the recent progress in speech processing, the majority of world languages and dialects remain uncovered. This situation only furthers an already wide technological divide, thereby hindering technological and socioeconomic inclusion. This challenge is largely due to the absence of dataset…

2023

Dolphin: A Challenging and Diverse Benchmark for Arabic NLG

EMNLP 2023long findings

We present Dolphin, a novel benchmark that addresses the need for a natural language generation (NLG) evaluation framework dedicated to the wide collection of Arabic languages and varieties. The proposed benchmark encompasses a broad range of 13 different NLG tasks, including dialogue generation, qu…

Cited by 0SourceScholar