Unverified50% confidenceFactExact time
Applying 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.
1
Sources
50%
Confidence
Long-term
Relevance
9/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMinor version upgrades are carried out through post-training techniques such as supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), or direct preference optimization (DPO), at a lower cost than full pretraining.68% 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68% similarUnverifiedIris adopts an SFT-RL climbing strategy, alternating between supervised fine-tuning and reinforcement learning, where high-quality behavioral trajectories discovered during the RL phase are fed back to the SFT phase as new supervision signals.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/919821API
curl https://kongchang.com/api/v1/knowledge/claims/919821MCP
get_claim(id=919821)