Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions
By: Junfeng Jiao , Saleh Afroogh , Kevin Chen and more
Potential Business Impact:
Tests if AI is safe for kids and teens.
As Large Language Models (LLMs) increasingly power applications used by children and adolescents, ensuring safe and age-appropriate interactions has become an urgent ethical imperative. Despite progress in AI safety, current evaluations predominantly focus on adults, neglecting the unique vulnerabilities of minors engaging with generative AI. We introduce Safe-Child-LLM, a comprehensive benchmark and dataset for systematically assessing LLM safety across two developmental stages: children (7-12) and adolescents (13-17). Our framework includes a novel multi-part dataset of 200 adversarial prompts, curated from red-teaming corpora (e.g., SG-Bench, HarmBench), with human-annotated labels for jailbreak success and a standardized 0-5 ethical refusal scale. Evaluating leading LLMs -- including ChatGPT, Claude, Gemini, LLaMA, DeepSeek, Grok, Vicuna, and Mistral -- we uncover critical safety deficiencies in child-facing scenarios. This work highlights the need for community-driven benchmarks to protect young users in LLM interactions. To promote transparency and collaborative advancement in ethical AI development, we are publicly releasing both our benchmark datasets and evaluation codebase at https://github.com/The-Responsible-AI-Initiative/Safe_Child_LLM_Benchmark.git
Similar Papers
Evaluating LLM Safety Across Child Development Stages: A Simulated Agent Approach
Computers and Society
Tests AI for kids' safety and understanding.
SafeLawBench: Towards Safe Alignment of Large Language Models
Computation and Language
Tests AI for safe and legal answers.
MinorBench: A hand-built benchmark for content-based risks for children
Computation and Language
Tests AI to keep kids safe from bad online stuff.