The talk given by Ahmet Üstün in KUIS AI Talks on March 12, 2024.

Title: Aya: An Open Science Initiative to Accelerate Multilingual AI Progress

Abstract:Access to cutting-edge breakthroughs in large language models (LLMs) has been limited to speakers of only a few, primarily English, languages. The Aya project aimed to change that by focusing on accelerating multilingual AI through an open-source initiative. This initiative resulted in a state-of-the-art multilingual instruction-tuned model and the largest multilingual instruction collection. Built by 3,000 independent researchers across 119 countries, the Aya collection is the largest of its kind, crafted through templating and translating existing NLP datasets across 114 languages. As part of this collection, the Aya dataset is the largest collection of original annotations from native speakers worldwide, covering 65 languages. Finally, trained on a diverse set of instruction mixtures, including the Aya collection and dataset, the Aya model is a multilingual language model that can follow instructions in 101 languages, achieving state-of-the-art performance in various multilingual benchmarks.

Short Bio: Ahmet Üstün is a research scientist at Cohere For AI. He has previously earned a PhD from the University of Groningen. His research interests are multi-task, multilingual, and efficient natural language processing with a particular focus on modular approaches and low-resource languages. He is one of the leading members of the AYA Open Science Initiative.