No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
Paper
•
2509.21880
•
Published
•
52
Thanh-Long V. Le
bltnynk
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 8 hours ago
Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset
upvoted
a
paper
about 1 month ago
When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM
Ensembling
upvoted
a
paper
about 1 month ago
Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement
Learning
Organizations
None yet
authored
a
paper
about 2 months ago