B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
Paper
•
2412.17256
•
Published
•
35
LLM-data
-
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
Paper • 2412.14922 • Published • 78Note noise检测 -> 去噪 -> 训练
NILE: Internal Consistency Alignment in Large Language Models
Paper • 2412.16686 • Published • 6Note sft数据与pre-train knowledge的一致性