SproutBench: A Benchmark for Safe and Ethical Large Language Models for Youth

TL;DR

SproutBench is a comprehensive benchmark designed to evaluate the safety and ethical considerations of large language models when used by children and adolescents, addressing gaps in age-specific risks.

Contribution

The paper introduces SproutBench, a novel evaluation suite with 1,283 prompts targeting developmental and safety risks specific to minors, and provides empirical analysis of 47 LLMs.

Findings

Substantial safety vulnerabilities in current LLMs for youth

Strong correlations between safety dimensions and risk factors

Inverse relationship between interactivity and age appropriateness

Abstract

The rapid proliferation of large language models (LLMs) in applications targeting children and adolescents necessitates a fundamental reassessment of prevailing AI safety frameworks, which are largely tailored to adult users and neglect the distinct developmental vulnerabilities of minors. This paper highlights key deficiencies in existing LLM safety benchmarks, including their inadequate coverage of age-specific cognitive, emotional, and social risks spanning early childhood (ages 0--6), middle childhood (7--12), and adolescence (13--18). To bridge these gaps, we introduce SproutBench, an innovative evaluation suite comprising 1,283 developmentally grounded adversarial prompts designed to probe risks such as emotional dependency, privacy violations, and imitation of hazardous behaviors. Through rigorous empirical evaluation of 47 diverse LLMs, we uncover substantial safety vulnerabilities, corroborated by robust inter-dimensional correlations (e.g., between Safety and Risk Prevention) and a notable inverse relationship between Interactivity and Age Appropriateness. These insights yield practical guidelines for advancing child-centric AI design and deployment.