SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems

arXiv:2603.17373 · cs.CL · Submitted 2026-03-18 · Read on arXiv

cs.CL

Submitted: 2026-03-18

Updated: 2026-09-23

Code: https://github.com/RadiantCrystal/SafeTutors

Terminology

• Alignment — 30× in this paper · explained in 1 episode
• Benchmark — 28× in this paper · explained in 2 episodes
• Scaffolding — 16× in this paper · explained in 3 episodes
• Calibration — 7× in this paper · explained in 7 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Cognitive Load — 5× in this paper · explained in 2 episodes
• Frustration — 4× in this paper · explained in 2 episodes
• Metacognition — 4× in this paper · explained in 5 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• External Validation — 3× in this paper · explained in 2 episodes
• Active Learning — 2× in this paper · explained in 6 episodes
• Adversarial Robustness — 2× in this paper · explained in 3 episodes
• Alignment Theory — 2× in this paper · explained in 1 episode
• Annotator Agreement — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 4 episodes
• Core — 2× in this paper · explained in 2 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptive Decoding — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Commentary — 1× in this paper · explained in 2 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Research Review — 1× in this paper · explained in 6 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Yi: Open Foundation Models by 01.AI
• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• Constitutional AI: Harmlessness from AI Feedback
• JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
• The Llama 3 Herd of Models
• ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
• Mistral 7B
• Mixtral of Experts
• CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
• Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
• Holistic Evaluation of Language Models
• MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
• Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
• TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models
• LearnLM: Improving Gemini for Learning
• Qwen2.5 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering