Tag: AI model robustness
Browse our exclusive articles!
Reducing LLM Biases with Debiasing Direct Preference Optimization
Discover how Debiasing-DPO reduces LLM biases from spurious social contexts, improving accuracy and fairness in high-stakes decision-making.
QUEST: Robust Query-Modulated Spherical Attention in Transformers
Discover QUEST, a stable and robust query-modulated spherical attention method enhancing Transformer training and performance across domains.
Adversarial Moral Stress Testing for Ethical AI Models
Discover how Adversarial Moral Stress Testing evaluates ethical robustness of large language models under multi-round adversarial interactions.
Adversarial Training for Semi-Supervised Text Classification
Boost semi-supervised text classification with adversarial training to improve model robustness, generalization, and use of unlabeled data effectively.
Defending Machine Learning Against Adversarial Attacks
Learn how adversarial examples threaten machine learning models and explore strategies to protect AI systems from deceptive attacks.