-
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA
Paper • 2505.21115 • Published • 135 -
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper • 2506.01939 • Published • 167 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 132
Pallavi W
Pallavi2114
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
None yet