Imagen de Portada

Curriculum Learning for Safety Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kumar, Sandeep, Smith, Virginia, Yadav, Chhavi
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Influence-based Attributions can be Manipulated
por: Yadav, Chhavi, et al.
Publicado: (2024)

Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice
por: Kuo, Kevin, et al.
Publicado: (2025)

Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences
por: Pattnaik, Pulkit, et al.
Publicado: (2024)

FairProof : Confidential and Certifiable Fairness for Neural Networks
por: Yadav, Chhavi, et al.
Publicado: (2024)

ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
por: Yadav, Chhavi, et al.
Publicado: (2025)

Automated Concept Discovery for LLM-as-a-Judge Preference Analysis
por: Wedgwood, James, et al.
Publicado: (2026)

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
por: Kuo, Kevin, et al.
Publicado: (2026)

The Blessing and Curse of Dimensionality in Safety Alignment
por: Teo, Rachel S. Y., et al.
Publicado: (2025)

DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
por: Wedgwood, James, et al.
Publicado: (2026)

Curriculum Abductive Learning
por: Hu, Wen-Chao, et al.
Publicado: (2025)

BSO: Safety Alignment Is Density Ratio Matching
por: Nguyen, Tien-Phat, et al.
Publicado: (2026)

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
por: Zhang, Jiawei, et al.
Publicado: (2025)

Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints
por: Low, Siow Meng, et al.
Publicado: (2024)

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
por: Lu, Haoran, et al.
Publicado: (2025)

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
por: Tan, Zhewen, et al.
Publicado: (2026)

Causally Aligned Curriculum Learning
por: Li, Mingxuan, et al.
Publicado: (2025)

Curriculum-Guided Antifragile Reinforcement Learning for Secure UAV Deconfliction under Observation-Space Attacks
por: Panda, Deepak Kumar, et al.
Publicado: (2025)

The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
por: Springer, Max, et al.
Publicado: (2026)

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
por: Feng, Jingyuan, et al.
Publicado: (2026)

Learning Versatile Skills with Curriculum Masking
por: Tang, Yao, et al.
Publicado: (2024)

Test-Time Safety Alignment
por: Saglam, Baturay, et al.
Publicado: (2026)

Learning to Play Blackjack: A Curriculum Learning Perspective
por: Alasti, Amirreza, et al.
Publicado: (2026)

Curriculum Learning for LLM Pretraining: An Analysis of Learning Dynamics
por: Elgaar, Mohamed, et al.
Publicado: (2026)

Probabilistic Curriculum Learning for Goal-Based Reinforcement Learning
por: Salt, Llewyn, et al.
Publicado: (2025)

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
por: Qu, Yuxiao, et al.
Publicado: (2026)

Curriculum-enhanced GroupDRO: Challenging the Norm of Avoiding Curriculum Learning in Subpopulation Shift Setups
por: Barbalau, Antonio
Publicado: (2024)

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
por: Cao, Chentao, et al.
Publicado: (2025)

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
por: Zhang, Yi, et al.
Publicado: (2025)

Curriculum Guided Personalized Subgraph Federated Learning
por: Kang, Minku, et al.
Publicado: (2025)

CLUTR: Curriculum Learning via Unsupervised Task Representation Learning
por: Azad, Abdus Salam, et al.
Publicado: (2022)

Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
por: Cai, Wang, et al.
Publicado: (2026)

PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment
por: Verma, Richa, et al.
Publicado: (2026)

Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment
por: Vega, Jason, et al.
Publicado: (2024)

Enhancing LLMs for Physics Problem-Solving using Reinforcement Learning with Human-AI Feedback
por: Anand, Avinash, et al.
Publicado: (2024)

AIMM: An AI-Driven Multimodal Framework for Detecting Social-Media-Influenced Stock Market Manipulation
por: Neela, Sandeep
Publicado: (2025)

Dual-Criterion Curriculum Learning: Application to Temporal Data
por: Abel, Gaspard, et al.
Publicado: (2026)

Proximal Curriculum with Task Correlations for Deep Reinforcement Learning
por: Tzannetos, Georgios, et al.
Publicado: (2024)

Principled Curriculum Learning using Parameter Continuation Methods
por: Pathak, Harsh Nilesh, et al.
Publicado: (2025)

Enhancing Spatio-temporal Quantile Forecasting with Curriculum Learning: Lessons Learned
por: Yin, Du, et al.
Publicado: (2024)

SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning
por: Hossain, Saad, et al.
Publicado: (2025)