CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models

TL;DR

This paper introduces CASTLE, a comprehensive benchmark for evaluating personalized safety in large language models, focusing on student-specific risks and attributes to improve safety assessments.

Contribution

It presents a novel benchmark with new metrics for assessing personalized safety in LLMs based on educational theories and diverse student attributes.

Findings

All tested models scored below 2.3 out of 5 in safety ratings.

CASTLE covers 15 safety risks and 14 student attributes with nearly 93,000 scenarios.

The benchmark reveals significant safety deficiencies in current LLMs.

Abstract

Large language models (LLMs) have advanced the development of personalized learning in education. However, their inherent generation mechanisms often produce homogeneous responses to identical prompts. This one-size-fits-all mechanism overlooks the substantial heterogeneity in students cognitive and psychological, thereby posing potential safety risks to vulnerable groups. Existing safety evaluations primarily rely on context-independent metrics such as factual accuracy, bias, or toxicity, which fail to capture the divergent harms that the same response might cause across different student attributes. To address this gap, we propose the concept of Student-Tailored Personalized Safety and construct CASTLE based on educational theories. This benchmark covers 15 educational safety risks and 14 student attributes, comprising 92,908 bilingual scenarios. We further design three evaluation metrics: Risk Sensitivity, measuring the model ability to detect risks; Emotional Empathy, evaluating the model capacity to recognize student states; and Student Alignment, assessing the match between model responses and student attributes. Experiments on 18 SOTA LLMs demonstrate that CASTLE poses a significant challenge: all models scored below an average safety rating of 2.3 out of 5, indicating substantial deficiencies in personalized safety assurance.