Large Language Models – Strengths and Opportunities

Speaker: Sunayana Sitaram

Abstract

In this talk, I will present a benchmarking view of understanding the capabilities of LLMs by discussing some recent results from large scale holistic benchmarking across many dimensions, including accuracy, fairness, bias, robustness and inclusivity.

Bio

Sunayana Sitaram is a Senior Researcher at Microsoft Research India. Her research goal is to enable inclusive universal empowerment through technology. Her current area of research is on making Large Language Models useful to everyone on the planet by improving their multilingual performance and infusing local culture and values. Sunayana also serves as the director of the MSR India Research Fellow program, which exposes bright young researchers to a world-class research environment and prepares them for careers in research, engineering and entrepreneurship. Prior to joining MSRI as a Post Doc Researcher, Sunayana completed her MS and PhD at the Language Technologies Institute, Carnegie Mellon University in 2015. Sunayana’s research has been published in top NLP and Speech conferences including ACL, NAACL, EMNLP, Interspeech, ICASSP and she regularly serves in the program committee of these conferences. In 2023, she will be serving as Industry track co-chair and Senior Area Chair for ACL 2023. She as organized special sessions and workshops on under-resourced languages, code-switching, multilingual evaluation and speech for social good. She has also led the creation of several benchmarks and datasets in code-switching, speech recognition and speech synthesis that have been used by research groups all over the world.