| Title | : | A Robust Approach to Classification and Truth-Validation: Incorporating Human and Large Language Model Decision Making |
| Speaker | : | Chaithanya Bandi (Faculty @ NUS, Singapore) |
| Details | : | Thu, 26 Oct, 2023 4:00 PM @ Google Meet |
| Abstract: | : | The advent of generative AI and foundational models has opened up promising avenues to enhance the efficiency of many service systems. However, their wider application has been stymied by the persistent presence of model errors and inaccuracies. These errors represent an intrinsic characteristic of current AI models, not just a transient hurdle. This talk presents a Robust Optimization-based approach that embraces this reality and seeks to optimize performance within this context.
We present a Robust optimization-based algorithmic framework and develop the Fast Algorithm for Classification and Truth-validation (FACT) to address the critical need for rigorous truth-validation in service systems. FACT is designed to leverage the decision-making competencies of both humans and foundational Large Language Models (LLMs) through a dynamic task routing strategy informed by task complexity, projected cost, and the capacity of the decision-making entity.
We present our results from a pilot implementation at an online education company's customer service portal, demonstrating significant efficiency benefits. This approach offers a promising trajectory for future research and practical implementations, especially in systems where AI and human decision-making must be effectively integrated.
Link : https://meet.google.com/epz-jekg-cwv |
