Work

Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions

Year: 2025

Type: preprint

Abstract: 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

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2506.13510

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

Institutions: The University of Texas at Austin, IBM (United States), Alliance for Safe Kids

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: green

Funder: National Science Foundation