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

• URL: http://arxiv.org/abs/2602.05633v1
• Date: Thu, 05 Feb 2026 13:13:19 GMT
• Title: CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
• Abstract summary: We propose the concept of Student-Tailored Personalized Safety and construct CASTLE based on educational theories.<n>This benchmark covers 15 educational safety risks and 14 student attributes, comprising 92,908 bilingual scenarios.
• Score: 55.0103764229311
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Sociodemographic Biases in Educational Counselling by Large Language Models [61.30199414932204]
  This study examines sociodemographic biases in Large Language Models (LLMs)<n>We evaluate responses from six LLMs answering questions about 900 vignettes describing students in diverse circumstances.
  arXiv  Detail & Related papers  (2026-04-03T14:08:22Z)
• Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model [50.29667251847595]
  We show that despite being larger in model size and stronger in safety capability, there exists an alignment gap between teacher and student language models.<n>We propose a BoN sampling method that attributes the unsafe behavior back to the base LLMs in the latent space.<n>In particular, across 7 teacher models and 6 student models of different classes and sizes, we show an average attack success rate (ASR) reduction of 28.2% in DAN, 31.3% in WildJailbreak and 35.4 % in StrongREJECT benchmarks.
  arXiv  Detail & Related papers  (2026-04-01T02:42:41Z)
• SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems [28.55608350602746]
  We introduce SafeTutors, a benchmark that jointly evaluates safety and pedagogy across mathematics, physics, and chemistry.<n>We uncover that all models show broad harm; scale doesn't reliably help; and multi-turn dialogue worsens behavior, with pedagogical failures rising from 17.7% to 77.8%.<n>Harms also vary by subject, so mitigations must be discipline-aware, and single-turn "safe/helpful" results can mask systematic tutor failure over extended interaction.
  arXiv  Detail & Related papers  (2026-03-18T05:33:50Z)
• SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond [134.43113804188195]
  We introduce SafeSci, a comprehensive framework for safety evaluation and enhancement in scientific contexts.<n>SafeSci comprises SafeSciBench, a multi-disciplinary benchmark with 0.25M samples, and SafeSciTrain, a large-scale dataset containing 1.5M samples for safety enhancement.
  arXiv  Detail & Related papers  (2026-03-02T08:16:04Z)
• SafeRBench: A Comprehensive Benchmark for Safety Assessment in Large Reasoning Models [60.8821834954637]
  We present SafeRBench, the first benchmark that assesses LRM safety end-to-end.<n>We pioneer the incorporation of risk categories and levels into input design.<n>We introduce a micro-thought chunking mechanism to segment long reasoning traces into semantically coherent units.
  arXiv  Detail & Related papers  (2025-11-19T06:46:33Z)
• EduGuardBench: A Holistic Benchmark for Evaluating the Pedagogical Fidelity and Adversarial Safety of LLMs as Simulated Teachers [8.123835490773095]
  Large Language Models for Simulating Professions (SP-LLMs) are pivotal for personalized education.<n>EduGuardBench assesses professional fidelity using a Role-playing Fidelity Score (RFS)<n>It also probes safety vulnerabilities using persona-based adversarial prompts targeting both general harms and, particularly, academic misconduct.
  arXiv  Detail & Related papers  (2025-11-10T09:42:24Z)
• Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models [0.0]
  This study proposes a unified framework for evaluating how resistant Large Language Models (LLMs) are to prompt injection attacks.<n>The framework defines three metrics such as the Resilience Degradation Index (RDI), Safety Compliance Coefficient ( SCC), and instructional Integrity Metric (IIM) to jointly measure robustness, safety, and semantic stability.
  arXiv  Detail & Related papers  (2025-11-03T14:43:56Z)
• What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift [33.83306492023009]
  ConceptLens is a generic framework that leverages pre-trained multimodal models to identify integrity threats.<n>It uncovers vulnerabilities to bias injection, such as the generation of covert advertisements through malicious concept shifts.<n>It uncovers sociological biases in generative content, revealing disparities across sociological contexts.
  arXiv  Detail & Related papers  (2025-04-28T13:30:48Z)
• The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 [70.94607997570729]
  We present a comprehensive safety assessment of OpenAI-o3 and DeepSeek-R1 reasoning models.<n>We investigate their susceptibility to adversarial attacks, such as jailbreaking and prompt injection, to assess their robustness in real-world applications.
  arXiv  Detail & Related papers  (2025-02-18T09:06:07Z)
• Safe to Serve: Aligning Instruction-Tuned Models for Safety and Helpfulness [0.0]
  Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning and text generation.<n>LLMs can inadvertently generate unsafe or biased responses when prompted with problematic inputs.<n>This research addresses the critical challenge of developing language models that generate both helpful and harmless content.
  arXiv  Detail & Related papers  (2024-11-26T06:52:22Z)
• ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Models [53.00812898384698]
  We argue that human evaluation of generative large language models (LLMs) should be a multidisciplinary undertaking. We highlight how cognitive biases can conflate fluent information and truthfulness, and how cognitive uncertainty affects the reliability of rating scores such as Likert. We propose the ConSiDERS-The-Human evaluation framework consisting of 6 pillars -- Consistency, Scoring Criteria, Differentiating, User Experience, Responsible, and Scalability.
  arXiv  Detail & Related papers  (2024-05-28T22:45:28Z)
• ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models [65.79770974145983]
  ASSERT, Automated Safety Scenario Red Teaming, consists of three methods -- semantically aligned augmentation, target bootstrapping, and adversarial knowledge injection. We partition our prompts into four safety domains for a fine-grained analysis of how the domain affects model performance. We find statistically significant performance differences of up to 11% in absolute classification accuracy among semantically related scenarios and error rates of up to 19% absolute error in zero-shot adversarial settings.
  arXiv  Detail & Related papers  (2023-10-14T17:10:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.