ASA Connect

 View Only

Upcoming Webinar on June 4th – SysChat: Leveraging Large Language Models to Answer System Questions with Citations with Cole Molloy

  • 1.  Upcoming Webinar on June 4th – SysChat: Leveraging Large Language Models to Answer System Questions with Citations with Cole Molloy

    Posted 06-02-2025 14:40
    Dear Colleagues,
     
    The ASA Section on Statistics in Defense and National Security (SDNS) is pleased to announce an upcoming webinar on LLMs as part of the SDNS Webinar Series.  The webinar will be held on this Wednesday, June 4th featuring Cole Molloy from the Johns Hopkins Applied Physics Laboratory (JHU/APL).  
    Title: SysChat: Leveraging Large Language Models to Answer System Questions with Citations
    Date: Wednesday, June 4th 
    Time: 2:00 – 3:00 PM EDT / 11:00 AM – Noon PDT

    Registration (Zoom, free): SDNS Webinar Registration

    Abstract:

    SysChat is a Retrieval Augmented Generation (RAG) tool that combines information retrieval with black-box large language models (LLMs) to answer user questions on mechanical systems. In retrieval-augmented generation, an embedding model first stores all documents in a vector database-in our case, tens of thousands of pages of complex systems documents. These embeddings are then used to identify relevant information for each query, guiding black-box LLM responses with improved factual accuracy and traceable information sources. This talk will discuss SysChat's architecture, highlighting classical and modern RAG techniques, LLM enhancements to improve reasoning capabilities, and a brief introduction to the transformer models that LLMs are built from.

    About the Speaker:

    Cole Molloy is a Data Scientist at the Johns Hopkins Applied Physics Laboratory, where he specializes in machine learning and natural language processing (NLP) to address complex scientific and engineering challenges. His work bridges theoretical research with practical applications, including software development for data handling, cleaning, report automation, and interactive visualization tools. Cole is currently pursuing his Ph.D. in Computer Science at Johns Hopkins University, where his research focuses on understanding the mechanisms through which NLP models attempt to encode social behaviors and using those mechanisms to better understand human-written texts.

    Contact:

    Interested in viewing past webinars or learning more about this webinar series? Visit SDNS Webinar Series or reach out to Elise Roberts (SDNS.AmStat@gmail.com) for more information!



    ------------------------------
    Elise Roberts
    Statistics in Defense and National Security
    https://community.amstat.org/sdns/home
    SDNS.AmStat@gmail.com
    ------------------------------