Taxonomy and Analysis of Sensitive User Queries in Generative AI Search
This work addresses the problem of managing sensitive content in generative AI search for industries, but it is incremental as it builds on existing practices with specific application insights.
The paper tackles the challenge of integrating generative LLMs into large-scale search engines by focusing on sensitive user queries, proposing a taxonomy and analyzing real user data to reduce barriers in deploying such services.
Although there has been a growing interest among industries in integrating generative LLMs into their services, limited experience and scarcity of resources act as a barrier in launching and servicing large-scale LLM-based services. In this paper, we share our experiences in developing and operating generative AI models within a national-scale search engine, with a specific focus on the sensitiveness of user queries. We propose a taxonomy for sensitive search queries, outline our approaches, and present a comprehensive analysis report on sensitive queries from actual users. We believe that our experiences in launching generative AI search systems can contribute to reducing the barrier in building generative LLM-based services.