EVALUATING LLM SAFETY ACROSS CHILD DEVELOPMENT STAGES: A SIMULATED AGENT APPROACH

Abhejay Murali, Saleh Afroogh, Kevin Chen, David Atkinson, Amit Dhurandhar, Junfeng Jiao

Keywords: LLM Safety, Child Development, Simulated Agents, AI alignment, Child Safety

Abstract: Current safety alignment for Large Language Models (LLMs) implicitly optimizes for a "modal adult user," leaving models vulnerable to distributional shifts in user cognition. We present ChildSafe, a benchmark that quantifies alignment robustness under cognitive shifts corresponding to four developmental stages. Unlike static persona-based evaluations, we introduce a parametric cognitive simulation approach, formalizing developmental stages as hyperparameter constraints (e.g., volatility, context horizon) to generate out-of-distribution interaction traces. We validate these agents against ground-truth human linguistic data (CHILDES) and deploy them across 1,200 multi-turn interactions. Our results reveal a systematic alignment generalization gap: state-of-the-art models exhibit up to 11.5% performance degradation when interacting with early-childhood agents compared to standard baselines. We provide the research community with the validated agent artifacts and evaluation protocols to facilitate robust alignment testing against non-adversarial, cognitively diverse populations

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 8126