Unverified50% confidenceFactExact time
The design of CIPR is not tied to a specific training paradigm and can be applied to both supervised fine-tuning (SFT) and reinforcement learning (RL) post-training stages.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCIPR is added to the total loss as a differentiable regularization term, requires no additional annotation, and does not change the convergence guarantees of the original training objective.75% similarUnverified继续预训练（CPT）是在通用基座模型上用领域语料进行额外的无监督训练，让模型吸收领域知识75% similarUnverifiedOffline RL trains a policy only on a pre-collected fixed dataset, with no further interaction with the environment during training, and its core advantage is that the training process is fully reproducible and auditable.71% 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71% similarUnverifiedPost-training is a critical phase between the completion of large language model pretraining and actual usability, encompassing technical approaches such as supervised fine-tuning (SFT), instruction alignment, and RLHF/DPO.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037942API
curl https://kongchang.com/api/v1/knowledge/claims/1037942MCP
get_claim(id=1037942)