MinorBench: A hand-built benchmark for content-based risks for children
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
CAREBench: A Child-Safety Risk Benchmark for Language Models
CAREBench is a new benchmark with 500 prompts in 12 risk categories that measures how often frontier LLMs fail to refuse or redirect child-safety risks, reporting failure rates between 2% and 58%.
-
Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions
Safe-Child-LLM supplies a new developmental benchmark dataset and evaluation protocol that exposes safety gaps in leading LLMs when handling child and adolescent users.
-
Child Safety in Generative AI: An Expert-Guided and Incident-Grounded Evaluation Framework
Proposes an expert-guided and incident-grounded framework for child safety evaluation in generative AI and applies it in education to find that Llama Guard models struggle with unsafe prompts.
-
Prompt Governance? On Governing Technologies Governed by Natural Language
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.