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.
@article{arxiv.2404.08672,
title = {Taxonomy and Analysis of Sensitive User Queries in Generative AI Search},
author = {Hwiyeol Jo and Taiwoo Park and Hyunwoo Lee and Nayoung Choi and Changbong Kim and Ohjoon Kwon and Donghyeon Jeon and Eui-Hyeon Lee and Kyoungho Shin and Sun Suk Lim and Kyungmi Kim and Jihye Lee and Sun Kim},
journal= {arXiv preprint arXiv:2404.08672},
year = {2025}
}
Comments
NAACL2025(Findings), corrected typo in co-corresponding authors