When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models Paper • 2512.04124 • Published 4 days ago • 1
Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning Paper • 2507.22565 • Published Jul 30 • 9
Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models Paper • 2504.03302 • Published Apr 4