Tag: adversarial machine learning
Browse our exclusive articles!
Boost LLM Code Refinement with Property-Oriented Feedback
Enhance LLM code accuracy using property-oriented, minimal feedback for better debugging and a 13%+ pass@1 improvement over traditional methods.
Exploration-Exploitation in LLMs vs Humans: Bandit Study
Explore how LLMs and humans differ in exploration-exploitation strategies using multi-armed bandit experiments and decision-making analysis.
System 1 Thinking in Large Reasoning Models Explained
Discover how large reasoning models perform fast, intuitive system 1 thinking and the challenges they face in accuracy and efficiency.
Understanding Representation in Large Language Models
Explore how large language models use representation vs. memorization to process language and their cognitive implications.
Efficient Last-Iterate Convergence in Constrained MDPs
Discover the PDR-ANPG algorithm for efficient last-iterate convergence in constrained Markov decision processes with improved sample complexity.