Abstract: 

Generative Large Language Models like GPT4 and ChatGPT are extremely powerful, but they hallucinate confidently. To build enterprise or end user applications, it is important to identify and address hallucination problems around such large language models. In this talk, I will cover the hallucination problem and how Truth Checker models can detect and deliver great and accurate experiences making it possible to use LLMs without human in the loop.

Bio: 

Chandra Khatri is the Chief Scientist and Head of AI at Got It AI, wherein, his team is transforming AI space by leveraging state-of-the-art technologies to deliver the world's first fully autonomous Conversational AI system. Under his leadership, Got It AI is democratizing Conversational AI and related ecosystems through automation. Prior to Got-It, Chandra was leading various AI applied and research groups at Uber, Amazon Alexa and eBay.

At Uber, he was leading Conversational AI, Multi-modal AI, and Recommendation Systems. At Amazon he was the founding member of the Alexa Prize Competition and Alexa AI, wherein he was leading the R&D and got the opportunity to significantly advance the field of Conversational AI, particularly Open-domain Dialog Systems, which is considered as the holy-grail of Conversational AI and is one of the open-ended problems in AI. And at eBay he was driving NLP, Deep Learning, and Recommendation Systems related applied research projects.

He graduated from Georgia Tech with a specialization in Deep Learning in 2015 and holds an undergraduate degree from BITS Pilani, India. His current areas of research include Artificial and General Intelligence, Democratization of AI, Reinforcement Learning, Language and Multi-modal Understanding, and Introducing Common Sense within Artificial Agents.