mlsanityData to 14 Oct 2026

SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs

arXiv 2604.22134 ↗First posted 24 Apr 2026cs.CLcited by 3

On the map: LLM safety and security → Safety alignment, refusal and guardrails

Abstract (arXiv)

Large Language Models (LLMs) have been widely explored in educational scenarios. We identify a critical vulnerability in current educational LLMs, pedagogical jailbreaks, where students use answer-inducing prompts to elicit solutions rather than scaffolded instructions. To enable systematic study, we unify and formalize safe, helpful, and pedagogical behaviors with a knowledge-mastery graph and introduce SHAPE, a benchmark of 9,087 student-question pairs for evaluating tutoring behavior under adversarial pressure. We propose a graph-augmented tutoring pipeline that infers prerequisite concepts from queries, identifies mastery gaps, and routes generation between instructing and problem-solving via explicit gating. Experiments across multiple LLMs show that our method yields significantly improved safety under two pedagogical jailbreak settings, while maintaining near-ceiling helpfulness under the same evaluation protocol. Our code and data are available at https://github.com/MAPS-research/SHaPE

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security. Builds on 20 of its 36 references that are in the map. First posted on arXiv 24 Apr 2026.

Builds on

20 of 36 references.

References · 20

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  3. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Ciphercited by 423
  4. 2015Deep Knowledge Tracingcited by 332
  5. 2025Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Taskcited by 106
  6. 2020Training Production Language Models without Memorizing User Datacited by 68
  7. 2024Enhancing LLM-Based Feedback: Insights from Intelligent Tutoring Systems and the Learning Sciencescited by 37
  8. 2025Enhancing Personalized Multi-Turn Dialogue with Curiosity Rewardcited by 27
  9. 2024Towards Modeling Learner Performance with Large Language Modelscited by 21
  10. 2025Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategiescited by 16
  11. 2025From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Educationcited by 9
  12. 2026Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoningcited by 7
8 more
  1. 2024PAIGE: Examining Learning Outcomes and Experiences with Personalized AI-Generated Educational Podcastscited by 5
  2. 2024AI Meets the Classroom: When Do Large Language Models Harm Learning?cited by 5
  3. 2025CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentationcited by 5
  4. 2025Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Educationcited by 5
  5. 2026Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Trainingcited by 3
  6. 2025Securing Educational LLMs: A Generalised Taxonomy of Attacks on LLMs and DREAD Risk Assessmentcited by 2
  7. 2026Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modelingcited by 2
  8. 2026Beyond Static Question Banks: Dynamic Knowledge Expansion via LLM-Automated Graph Construction and Adaptive Generationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Mitigating Scaffolding Collapse in Socratic Tutors via Representation Alignmentcited by 0
  2. 2026Auditable Release Control for Pedagogical Leakage in LLM Tutorscited by 0
  3. 2026ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks
  2. 2026EduZone: A Framework for Evaluating LLM Safety for K-12 Students and Teachers
  3. 2026SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems
  4. 2024Student Data Paradox and Curious Case of Single Student-Tutor Model: Regressive Side Effects of Training LLMs for Personalized Learning
  5. 2024Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
  6. 2024Give me a hint: Can LLMs take a hint to solve math problems?
  7. 2026The Tutoring Effectiveness Index: Predicting LLM Math Tutor Quality from Four Conversation Signals
  8. 2024AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails