MinorBench: A hand-built benchmark for content-based risks for children
This addresses content-based risks for children using LLMs, though it is incremental as it builds on existing safety frameworks with a new benchmark.
The paper tackles the lack of AI safety research for children by introducing MinorBench, a benchmark to evaluate LLMs on refusing unsafe queries from minors, showing substantial variability in child-safety compliance across six models.
Large Language Models (LLMs) are rapidly entering children's lives - through parent-driven adoption, schools, and peer networks - yet current AI ethics and safety research do not adequately address content-related risks specific to minors. In this paper, we highlight these gaps with a real-world case study of an LLM-based chatbot deployed in a middle school setting, revealing how students used and sometimes misused the system. Building on these findings, we propose a new taxonomy of content-based risks for minors and introduce MinorBench, an open-source benchmark designed to evaluate LLMs on their ability to refuse unsafe or inappropriate queries from children. We evaluate six prominent LLMs under different system prompts, demonstrating substantial variability in their child-safety compliance. Our results inform practical steps for more robust, child-focused safety mechanisms and underscore the urgency of tailoring AI systems to safeguard young users.