3 papers
cs.CL2026
UrduBench: An Urdu Reasoning Benchmark using Contextually Ensembled Translations with Human-in-the-Loop
Muhammad Ali Shafique, Areej Mehboob, Layba Fiaz +2
Recent advances in large language models (LLMs) have led to strong reasoning capabilities; however, evaluating such models in low-resource languages remains challenging due to the…
cs.CL2025
UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings
Layba Fiaz, Munief Hassan Tahir, Sana Shams +1
Multilingual Large Language Models (LLMs) often provide suboptimal performance on low-resource languages like Urdu. This paper introduces UrduLLaMA 1.0, a model derived from the op…
cs.CL2024
Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks
Munief Hassan Tahir, Sana Shams, Layba Fiaz +2
Large Language Models (LLMs) pre-trained on multilingual data have revolutionized natural language processing research, by transitioning from languages and task specific model pipe…