Tag: adversarial machine learning
Browse our exclusive articles!
Optimize LLM Reinforcement Learning with Reasoning Trees
Boost LLM accuracy using Reasoning Tree scheduling and the new Reasoning Score for efficient reinforcement learning.
Multi-Subspace Steering for Precise LLM Attribute Control
Discover how Multi-Subspace Representation Steering enhances Large Language Models by reducing attribute conflicts and improving control precision.
Is Chain-of-Thought Reasoning in LLMs Truly Reliable?
Explore if Chain-of-Thought reasoning in large language models is robust or just an illusion through a data distribution perspective.
Enhancing AI Learning with Multiple Thinkers’ Insights
Discover how AI improves problem-solving by learning from multiple thinkers using Chain-of-Thought supervision and active learning algorithms.
Efficient Ensemble Training with Auto Learning Rate for Large Models
Discover scalable ensemble training using automatic learning rate exploration to optimize large model performance and hyperparameter tuning efficiently.