Proposes an expert-guided and incident-grounded framework for child safety evaluation in generative AI and applies it in education to find that Llama Guard models struggle with unsafe prompts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Child Safety in Generative AI: An Expert-Guided and Incident-Grounded Evaluation Framework
Proposes an expert-guided and incident-grounded framework for child safety evaluation in generative AI and applies it in education to find that Llama Guard models struggle with unsafe prompts.