Unverified50% confidenceFactExact time
SFT cold start refers to first using supervised fine-tuning to give the model basic target behavior patterns before reinforcement learning, in order to avoid the extremely sparse reward signal problem when RL explores from scratch.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDuring the pretraining phase, the model's objective function is typically to maximize the log-likelihood of the next token and does not include signals for refusing to answer.70% similarUnverifiedProbe guidance extracts guidance signals directly from the frozen internal states of existing models, eliminating the need for additional forward passes during inference.69% similarVerifiedSupervised Fine-Tuning (SFT) trains the model using 'prompt-response' example pairs, teaching the model to respond in a conversational format, thereby making outputs more coherent.69% similarVerifiedDomain fine-tuning typically first injects domain knowledge through supervised fine-tuning (SFT), then aligns with user preferences through reinforcement learning from human feedback (RLHF).69% similarUnverifiedZero-shot learning refers to a model making predictions at inference time without relying on any labeled samples for the task, directly based on pre-trained knowledge or external structural information.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023951API
curl https://kongchang.com/api/v1/knowledge/claims/1023951MCP
get_claim(id=1023951)