3 Steps to Create Trustworthy Generative AI Products- Sohini Roychowdhury | Compass Tech Summit 2023

Unveiling the 3 Steps to Create Sustainable and Trustworthy Generative AI Products for Finance-Based Use Cases - Sohini Roychowdhury, Generative AI Capability Lead for Analytical Data products at Accenture USA
Generative Ai chatbots have become increasingly popular over the last year with the launch of
OpenAI’s Chatgpt. However, the current trend for operationalizing foundational large language
models (LLMs) that are used in chatbots and fine-tuning them to specific domains have revealed
the fake responses or hallucinations specifically for mathematical operations. Thus, designing
chatbot-like products for finance-based use cases without controlling for hallucinations can have
the most detrimental impact on its decision-making users. In this talk we review the three major
stages in designing and delivering hallucination minimized chatbot solutions for use cases where
the input data is in the form of large tables. In the first prototyping stage, we control the language
data generation process and build a scoring engine for the chatbot responses to minimize
hallucinations. In the second scaling stage, we focus on the scalability, robustness, cost-per-
query, and trustworthiness of the overall LLM-based system architecture with the growing data
needs. The third evolution stage involves reinforcement learning with human feedback to learn to
execute complex financial instructions over time. A LLM system that is designed with these
stages under consideration will stay sustainable to LLM modifications over time and evolve in
functionality for domain specific use cases.
This talk was recorded at Compass Tech Summit 2023.
The event was organized by Crafthub.
You can watch the rest of the conference talks on our channel.
If you are interested in more speakers, tickets and details of the conference, check out our website: reinforceconf....
If you are interested in more events from our company: crafthub.events/