Cover Image

SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hazra, Rima, Ghuku, Bikram, Marchenko, Ilona, Tokarieva, Yaroslava, Layek, Sayan, Banerjee, Somnath, Stoyanovich, Julia, Pechenizkiy, Mykola
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models
by: Banerjee, Somnath, et al.
Published: (2025)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
by: Hazra, Rima, et al.
Published: (2024)

SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
by: Banerjee, Somnath, et al.
Published: (2024)

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
by: Hazra, Rima, et al.
Published: (2024)

How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
by: Banerjee, Somnath, et al.
Published: (2024)

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
by: Banerjee, Somnath, et al.
Published: (2025)

Tutoring Large Language Models to be Domain-adaptive, Precise, and Safe
by: Banerjee, Somnath
Published: (2026)

Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations
by: Banerjee, Somnath, et al.
Published: (2025)

Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context
by: Banerjee, Somnath, et al.
Published: (2024)

Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages
by: Banerjee, Somnath, et al.
Published: (2026)

Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
by: Banerjee, Somnath, et al.
Published: (2024)

MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
by: Adak, Sayantan, et al.
Published: (2025)

SafeMath: Inference-time Safety improves Math Accuracy
by: Basu, Sagnik, et al.
Published: (2026)

"Would You Want an AI Tutor?" Understanding Stakeholder Perceptions of LLM-based Systems in the Classroom
by: Fuligni, Caterina, et al.
Published: (2025)

Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors
by: Maurya, Kaushal Kumar, et al.
Published: (2024)

MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
by: Macina, Jakub, et al.
Published: (2025)

BIPED: Pedagogically Informed Tutoring System for ESL Education
by: Kwon, Soonwoo, et al.
Published: (2024)

LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring
by: Lee, Unggi, et al.
Published: (2026)

Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
by: Banerjee, Somnath, et al.
Published: (2026)

Intent Matters: Enhancing AI Tutoring with Fine-Grained Pedagogical Intent Annotation
by: Petukhova, Kseniia, et al.
Published: (2025)

Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
by: Banerjee, Somnath, et al.
Published: (2024)

Redefining Developer Assistance: Through Large Language Models in Software Ecosystem
by: Banerjee, Somnath, et al.
Published: (2023)

Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions
by: Liu, Zhengyuan, et al.
Published: (2024)

Evaluating the Ebb and Flow: An In-depth Analysis of Question-Answering Trends across Diverse Platforms
by: Hazra, Rima, et al.
Published: (2023)

DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem
by: Banerjee, Somnath, et al.
Published: (2024)

PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning
by: Chang, Qikai, et al.
Published: (2026)

MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring
by: Yang, Tengchao, et al.
Published: (2025)

Findings of the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors
by: Kochmar, Ekaterina, et al.
Published: (2025)

From Solver to Tutor: Evaluating the Pedagogical Intelligence of LLMs with KMP-Bench
by: Shi, Weikang, et al.
Published: (2026)

BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses
by: Rohan, Shadman, et al.
Published: (2025)

AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models
by: Adak, Sayantan, et al.
Published: (2025)

DeepTutor: Towards Agentic Personalized Tutoring
by: Zhao, Bingxi, et al.
Published: (2026)

Generative AI and Its Impact on Personalized Intelligent Tutoring Systems
by: Maity, Subhankar, et al.
Published: (2024)

Pedagogy-driven Evaluation of Generative AI-powered Intelligent Tutoring Systems
by: Maurya, Kaushal Kumar, et al.
Published: (2025)

AITutor-EvalKit: Exploring the Capabilities of AI Tutors
by: Naeem, Numaan, et al.
Published: (2025)

Tutor Move Taxonomy: A Theory-Aligned Framework for Analyzing Instructional Moves in Tutoring
by: Zhou, Zhuqian, et al.
Published: (2026)

Can Large Language Models Match Tutoring System Adaptivity? A Benchmarking Study
by: Borchers, Conrad, et al.
Published: (2025)

Everyone deserves their voice to be heard: Analyzing Predictive Gender Bias in ASR Models Applied to Dutch Speech Data
by: Raes, Rik, et al.
Published: (2024)

Language Models as Science Tutors
by: Chevalier, Alexis, et al.
Published: (2024)

Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems
by: Olukola, Oluseyi, et al.
Published: (2026)