Menu
Paula Payton
Paula Payton

Paula Payton

Senior Manager Center for Machine and Data Science
Deloitte Services LLP
Bio

Paula is a Senior Manager with Deloitte Services LLP where she leads the Center for Machine Intelligence and Data Science (MInDS), a multidisciplinary team of data scientists ,behavioral scientists, and survey specialists that support thought leadership from seven major research centers at the firm

A technical leader, management expert, social scientist, and educator, she  has held leadership roles in both industry and academia and is expert at using data, analytics and behavioral science to help organizations unlock insights .

In addition to her industry work, she is a longstanding data acience and analytics professor  and active in teaching and guiding the next generation of analytics , data science and AI talent. She has held academic appointments at  Wake Forest University School of Business, Columbia University and NYU, and mentors graduate students at the University of Chicago ‘s Data Science Institute. and Columbia Data Science Society.

Her current research interests include developing AI tools to transform research and analysis, as well as incorporating behavioral science insights into AI models and systems

Paula holds a PhD in Management (NEOMA Business School), and an MA in Behavioral Science  (University of Chicago) with graduate diplomas in data science  (Johns Hopkins University) and corporate strategy (Cornell University University Johnson School of Management)


Question based Retrieval Augmented Generation (QRAG) : Evaluating a New Approach to Retrieval-Augmented Generation (RAG)

Featuring: Sandeep Vellanki

Large Language Models (LLMs), a subset of natural language processing (NLP), enable sophisticated text generation, comprehension, and reasoning. However, LLMs often suffer from issues like hallucinations, outdated knowledge, and high computational costs.  Retrieval-Augmented Generation (RAG) has emerged as a powerful solution to mitigate these limitations since they were first introduced in 2021.  RAG systems combine the ability to dynamically retrieve information from an external knowledge base and then generate contextual and coherent responses based on the retrieved information..  However, RAG models are not without their challenges, which include latency, retrieval noise, and optimization issues.  In this presentation, we explore a new approach to RAG – a question-based RAG or QRAG  – that can enhance efficiency and accuracy while maintaining or improving response quality. We then compare traditional LLMs and standard RAGs with our new QRAG approach, analyzing key benchmarks such as latency, precision, and relevance scoring. We close with a discussion of possible use cases and applications for QRAGs, as well as future research directions.

Back To Top

Institute for Operations Research and the Management Sciences

5521 Research Park Drive, Suite 200
Catonsville, MD 21228 USA

phone 1 443-757-3500

phone 2 800-4INFORMS (800-446-3676)

fax 443-757-3515

email

Get the Latest Updates

Copyright 2025 INFORMS. All Rights Reserved