Tag: adversarial machine learning
Browse our exclusive articles!
Enhancing Reinforcement Learning with Contrastive Rewards
Discover ConSPO, a novel contrastive framework improving reinforcement learning with verifiable rewards for better AI reasoning and performance.
Expressivity Limits of Probabilistic Circuits vs Large Language Models
Explore the expressivity boundaries of Probabilistic Circuits compared to Large Language Models and their impact on natural language processing.
Optimizing Data Difficulty for LLM Fine-Tuning Success
Discover how data difficulty impacts LLM fine-tuning and the tradeoff between generalization and extrapolation for better model performance.
Bayesian Model Merging: Efficient AI Model Integration
Discover Bayesian Model Merging, a novel AI technique improving multi-task model integration with optimized hyperparameters and strong priors.
REALISTA: Realistic Attacks Triggering LLM Hallucinations
Discover REALISTA, a novel framework creating realistic adversarial prompts to expose and mitigate hallucinations in large language models (LLMs).