Cover Image

SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Sihang, Yu, Kangrui, Yuan, Youliang, He, Pinjia, Wen, Hongyi
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

Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs
by: Zhao, Sihang, et al.
Published: (2024)

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
by: Yuan, Youliang, et al.
Published: (2024)

PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning
by: Zhao, Yusong, et al.
Published: (2026)

Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs
by: Wang, Wenxuan, et al.
Published: (2025)

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
by: Yuan, Youliang, et al.
Published: (2023)

Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs
by: Liu, Xiaoyuan, et al.
Published: (2024)

Towards Evaluating Proactive Risk Awareness of Multimodal Language Models
by: Yuan, Youliang, et al.
Published: (2025)

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
by: Yuan, Youliang, et al.
Published: (2025)

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
by: Wan, Yuxuan, et al.
Published: (2024)

Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs
by: Huang, Jen-Tse, et al.
Published: (2025)

SHAPE-IT: Exploring Text-to-Shape-Display for Generative Shape-Changing Behaviors with LLMs
by: Qian, Wanli, et al.
Published: (2024)

Black-Box Segmentation of Electronic Medical Records
by: Yuan, Hongyi, et al.
Published: (2024)

BackportBench: A Multilingual Benchmark for Automated Backporting of Patches
by: Zhong, Zhiqing, et al.
Published: (2025)

HalluClean: A Unified Framework to Combat Hallucinations in LLMs
by: Zhao, Yaxin, et al.
Published: (2025)

An Analysis of Large Language Models for Simulating User Responses in Surveys
by: Yu, Ziyun, et al.
Published: (2025)

SAFER: Probing Safety in Reward Models with Sparse Autoencoder
by: Shi, Wei, et al.
Published: (2025)

Can Hallucinations Help? Boosting LLMs for Drug Discovery
by: Yuan, Shuzhou, et al.
Published: (2025)

UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench
by: Yu, Boxi, et al.
Published: (2025)

HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness
by: Wang, Xinyi, et al.
Published: (2025)

All Languages Matter: On the Multilingual Safety of Large Language Models
by: Wang, Wenxuan, et al.
Published: (2023)

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
by: Chehbouni, Khaoula, et al.
Published: (2024)

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
by: Luo, Xuan, et al.
Published: (2025)

Safe to Serve: Aligning Instruction-Tuned Models for Safety and Helpfulness
by: Amballa, Avinash, et al.
Published: (2024)

Aligning the Objective of LLM-based Program Repair
by: Xu, Junjielong, et al.
Published: (2024)

Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
by: Fu, Yu, et al.
Published: (2024)

Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs
by: Soligo, Anna, et al.
Published: (2026)

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
by: Li, Changyue, et al.
Published: (2025)

Let AI Read First: Enhancing Reading Abilities for Individuals with Dyslexia through Artificial Intelligence
by: Zhao, Sihang, et al.
Published: (2025)

Does Using Counterfactual Help LLMs Explain Textual Importance in Classification?
by: Tan, Nelvin, et al.
Published: (2025)

When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation
by: Ni, Shiyu, et al.
Published: (2024)

Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench
by: Huang, Jen-tse, et al.
Published: (2023)

When Irregularity Helps: A Subclass Analysis of Inductive Bias in Neural Morphology
by: Zhang, Wen
Published: (2026)

Safety Training Persists Through Helpfulness Optimization in LLM Agents
by: Plaut, Benjamin
Published: (2026)

From "Help" to Helpful: A Hierarchical Assessment of LLMs in Mental e-Health Applications
by: Steigerwald, Philipp, et al.
Published: (2026)

Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs
by: Arnaiz-Rodriguez, Adrian, et al.
Published: (2025)

UniEDU: A Unified Language and Vision Assistant for Education Applications
by: Chu, Zhendong, et al.
Published: (2025)

Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark
by: Lee, Unggi, et al.
Published: (2025)

IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages
by: Azmi, Muhammad Falensi, et al.
Published: (2025)

Scalable Supervising Software Agents with Patch Reasoner
by: Xu, Junjielong, et al.
Published: (2025)

Intrinsic Entropy of Context Length Scaling in LLMs
by: Shi, Jingzhe, et al.
Published: (2025)