-
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA
Paper • 2505.21115 • Published • 144 -
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper • 2506.01939 • Published • 190 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 146
Pallavi W PRO
Pallavi2114
AI & ML interests
None yet
Organizations
None yet
PapersToRead
-
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA
Paper • 2505.21115 • Published • 144 -
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper • 2506.01939 • Published • 190 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 146
models 0
None public yet
datasets 0
None public yet