The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation Paper • 2604.16830 • Published Apr 18 • 15
Didactic to Constructive: Turning Expert Solutions into Learnable Reasoning Paper • 2602.02405 • Published Feb 2 • 2
Do Vision-Language Models Respect Contextual Integrity in Location Disclosure? Paper • 2602.05023 • Published Feb 4 • 2
Training Socially Aligned Language Models in Simulated Human Society Paper • 2305.16960 • Published May 26, 2023 • 4
Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation Paper • 2404.09127 • Published Apr 14, 2024 • 2
VLGuard Collection Data and Model weights for VLGuard: https://ys-zong.github.io/VLGuard/ • 13 items • Updated Jun 18, 2024 • 1
