Explore a cutting-edge approach to detoxifying query auto-completion in this 14-minute conference talk from SIGIR 2024. Delve into the Quantized Optimal Transport Reward-based Reinforcement Learning method, presented by authors Aishwarya Maheswaran, Kaushal Maurya, Manish Gupta, and Maunendra Sankar Desarkar. Learn how this innovative technique addresses the challenge of toxic language in natural language processing, specifically in query auto-completion systems. Gain insights into the integration of quantized optimal transport and reinforcement learning to create more user-friendly and ethically responsible auto-complete suggestions.