The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents Paper • 2601.07264 • Published 4 days ago • 22
Alt-Text with Context: Improving Accessibility for Images on Twitter Paper • 2305.14779 • Published May 24, 2023
RLCD: Reinforcement Learning from Contrast Distillation for Language Model Alignment Paper • 2307.12950 • Published Jul 24, 2023 • 10