Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 135 •
22
Li Pengyi
LiPengyi29
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
How Far Can Unsupervised RLVR Scale LLM Training? upvoted a paper about 1 month ago
Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities submitted a paper about 1 month ago
Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative ProbabilitiesOrganizations
commented 5
papers 9 months ago
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 135 •
22
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 135 •
22
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 135 •
22
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 135 •
22