The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models
For developers and regulators of child-facing AI, this provides a much-needed benchmark and reveals that current LLMs lack adequate child safety, with significant room for improvement.
The paper introduces KIDBench, a benchmark for evaluating child-facing safety in LLMs for ages 7-11, and finds that implicit cues improve safety scores by 9-47% and explicit age instructions add 10-30% further gain, while multi-turn simulations show degradation of 6-24%.
Children increasingly have access to Large Language Models (LLMs), which may expose them to responses that are developmentally inappropriate or require age-sensitive safety, guidance, and boundaries. Existing LLM safety evaluations largely focus on harmful-content avoidance and do not explicitly target child-facing safety. We introduce KIDBench, a benchmark for evaluating child-facing LLM safety for ages 7--11 using a developmental-psychology-grounded LLM-as-a-Judge rubric. KIDBench contains realistic child queries across ten categories, with single-turn prompts and multi-turn child-actor simulations. We compare no-cues prompts with no child context, implicit-cues prompts that suggest a child speaker, and explicit age instructions. Implicit-cues improve scores by 9--47% across models, while explicit age adds a further 10--30% gain. Cross-lingual and cultural evaluations show uneven safety behavior across languages and country contexts. Multi-turn simulations show that child-facing response quality can degrade by 6--24% from the first to worst turn. Beyond evaluation, we introduce KIDGuardLlama, a child-safety evaluator, and KIDLlama, a child-oriented response model, showing how KIDBench supports safer child-facing AI