Arushi Jain

Arushi Jain

Applied Scientist (AI & ML) at Microsoft Corporation

    Arushi is a Applied Machine Learning Scientist working on M365 Copilot with a focus on Language Understanding and Search Relevance in Microsoft Search Assistant & Intelligence (MSAI) Team. Prior to this, she was part of Microsoft's 2-year AI Rotational program (MAIDAP) where she built AI product features every 6 months with 4 Microsoft product groups. She holds a Masters degree in Machine Learning from the University of Michigan Ann Arbor and a Bachelors-Masters (Dual) degree in Economics from IIT Kanpur. She has led the Michigan Alexa Prize Team and received a 250,000$ research grant to create an active listening and personalized socialbot. During her graduate and undergraduate studies, she had the privilege to collaborate with Researchers at Stanford HAI, Rutgers School of Information, Virginia Tech Economics Department and UCLA Social Comp lab. Besides that, she is deeply passionate about bringing more women and non-binary to AI and is dedicated to changing the GENDER IMBALANCE in the Tech industry. She leads the Women in Data Science (WiDS) community for Cambridge, where she single-handedly scaled Machine learning workshops from just 25 women in 2020 to 100+ in 2023.

    All Sessions by Arushi Jain

    Day 3 04/25/2024
    2:00 pm - 2:30 pm

    Copilot: Generative AI and Large Language Models.

    <span class="etn-schedule-location"> <span class="firstfocus">LLMs</span> </span>

    Copilot or AI agents are getting useful daya by day by enhancing our productivity and creativity in mundane tasks. I will start the talk with Evolution of Large Language Models (LLMs) covering different techniques and historical benchmarks in the NLP field. Next, I will dive deeper into the concept of Copilot, how it's useful to us and different applications for Copilot today. The core of any AI agent system is Language understanding so will explain what Language Understanding is through an example and how it works in M365 Copilot today. Lastly, I will cover some strategies for using LLMs for Language Understanding like Dynamic Prompting and Fine Tuning which helps in making a robust domain tagging mechanism to improve Search quality in Copilots/AI agents along with some limitations of Fine Tuning LLMs.

    Open Data Science




    Open Data Science
    One Broadway
    Cambridge, MA 02142

    Privacy Settings
    We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
    Consent to display content from - Youtube
    Consent to display content from - Vimeo
    Google Maps
    Consent to display content from - Google