Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models Paper • 2506.06395 • Published Jun 5, 2025 • 133
MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation Paper • 2506.14028 • Published Jun 16, 2025 • 93
UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities Paper • 2507.19766 • Published Jul 26, 2025 • 14
