Unverified50% confidenceFactExact time
The paper's experiments show that supervised fine-tuning (SFT) can make preferences learnable.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedApplying reinforcement learning starting from a repaired SFT checkpoint yields larger and more stable performance gains, indicating a synergistic effect between repairing first and reinforcing afterward.73% similarVerified从预训练检查点到可商用产品需经历监督式指令微调（SFT）和基于人类反馈的强化学习（RLHF）两个后训练阶段72% similarUnverifiedFor classification tasks with discrete and closed label spaces, the training signal from SFT is already clear enough, and introducing reinforcement learning would instead increase the difficulty of hyperparameter tuning and training instability71% similarVerifiedLarge model training goes through three core stages: pre-training, supervised fine-tuning (SFT), and preference alignment.70% similarUnverified后训练通常涵盖监督微调（SFT）、强化学习对齐（RLHF/RLAIF）以及领域适配微调，视觉推理模型还涉及视觉指令微调70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041750API
curl https://kongchang.com/api/v1/knowledge/claims/1041750MCP
get_claim(id=1041750)