LLM Safety for Children

TL;DR

This paper evaluates the safety of Large Language Models for children under 18, identifying risks and proposing child-specific user models to assess and improve safety in LLM interactions with minors.

Contribution

It introduces Child User Models based on child psychology to evaluate LLM safety specifically for children, highlighting safety gaps in current models.

Findings

Significant safety gaps identified in LLMs for children

Child User Models effectively evaluate safety risks

Potential content harms specific to children are highlighted

Abstract

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