# LLM Safety for Children

arXiv: https://arxiv.org/abs/2502.12552 · HTML: https://mlsanity.com/paper/2502.12552/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 9 of 9)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Inverse Scaling: When Bigger Isn't Better](https://mlsanity.com/paper/2306.09479/) (2023)
- [ChaCha: Leveraging Large Language Models to Prompt Children to Share Their Emotions about Personal Events](https://mlsanity.com/paper/2309.12244/) (2023)
- [Helpful or Harmful? Exploring the Efficacy of Large Language Models for Online Grooming Prevention](https://mlsanity.com/paper/2403.09795/) (2024)
- [Online Suicide Games: A Form of Digital Self-harm or A Myth?](https://mlsanity.com/paper/2012.00530/) (2020)

## Built on by (most cited first, 5 of 5)

- [The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behavior](https://mlsanity.com/paper/2509.19364/) (2025)
- [Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions](https://mlsanity.com/paper/2506.13510/) (2025)
- [CAREBench: A Child-Safety Risk Benchmark for Language Models](https://mlsanity.com/paper/2606.29685/) (2026)
- [Adversarial Reframing: A Framework for Targeted Generation in Language Models](https://mlsanity.com/paper/2605.21674/) (2026)
- [KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models](https://mlsanity.com/paper/2605.26947/) (2026)

## Abstract (arXiv)

This paper analyzes the safety of Large Language Models (LLMs) in interactions with children below age of 18 years. Despite the transformative applications of LLMs in various aspects of children's lives such as education and therapy, there remains a significant gap in understanding and mitigating potential content harms specific to this demographic. The study acknowledges the diverse nature of children often overlooked by standard safety evaluations and proposes a comprehensive approach to evaluating LLM safety specifically for children. We list down potential risks that children may encounter when using LLM powered applications. Additionally we develop Child User Models that reflect the varied personalities and interests of children informed by literature in child care and psychology. These user models aim to bridge the existing gap in child safety literature across various fields. We utilize Child User Models to evaluate the safety of six state of the art LLMs. Our observations reveal significant safety gaps in LLMs particularly in categories harmful to children but not adults