Dan Saattrup Nielsen
PhD student at Alexandra Instituttet
Presentation on the benchmarking of LLMs, with a specific application to the Northern European languages. The challenges of evaluating generative language models, the different ways in which this can be done, and the current status within the Northern European language will be presented. This is followed by an introduction to the ScandEval evaluation framework, which supports all these Northern European languages, and concludes with a presentation of the results of benchmarking models across languages.
Keywords: Large Language Model (LLM), Trustworthy AI, Natural Language Processing (NLP), Multilingual Germanic Language Family, Low-resource Languages
Scientific area: Artificial Intelligence
Bio: I am a data scientist with specialised knowledge of machine learning methods, in particular Natural Language Processing (NLP) and Graph Neural Networks. I have a PhD in Mathematics and have a strong interest within Scandinavian NLP. With a background in both academia and industry, I am in tune with the demands of each. I am incredibly ambitious and love what I am doing, and I tend to take a lot of initiative to new projects and to look at things from new angles.
Visiting period: 03.06.-05.06.2024 at Instituto Superior Técnico