collaborators

5 papers

cs.LG2026

\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating

Jianghui Wang, Silong Yong, Francesco Orabona +3

Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matrices. However, LoRA remains c…

cs.CL2026

Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures

Tyler A. Chang, Catherine Arnett, Abdelrahman Sadallah +377

To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we pre…

cs.LG2026

Nonparametric Teaching of Attention Learners

Chen Zhang, Jianghui Wang, Bingyang Cheng +7

Attention learners, neural networks built on the attention mechanism, e.g., transformers, excel at learning the implicit relationships that relate sequences to their corresponding…

cs.CL2026

Mix, MinHash, and Match: Cross-Source Agreement for Multilingual Pretraining Datasets

Sultan Alrashed, Francesco Orabona

Multilingual data from the web is essential for LLM pretraining. Yet, scraping it is expensive, and research groups repeatedly crawl the same content. For example, we found that ov…

cs.CL2025

SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data

Sultan Alrashed, Chadi Helwe, Francesco Orabona

Although the community has tackled the acquisition of high-quality Arabic pretraining data, we still lack large-scale, multi-turn Arabic datasets that include reasoning and tool ca…