Search papers, labs, and topics across Lattice.
The paper introduces Safe-Child-LLM, a new benchmark and dataset designed to evaluate the safety of LLMs when interacting with children (7-12) and adolescents (13-17). It uses 200 adversarial prompts, derived from existing red-teaming datasets, with human annotations for jailbreak success and ethical refusal scores. Evaluations of prominent LLMs reveal significant safety vulnerabilities in child-facing scenarios, highlighting the necessity for specialized benchmarks.
LLMs like ChatGPT, Claude, and Gemini show alarming safety gaps when interacting with children, readily bypassing ethical safeguards designed for adults.
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
