Unverified50% confidenceFactExact time
In multi-step tool-calling tasks, SFT provides the initial policy and reasoning format, while RL is responsible for fine-tuning the decision boundary under reward guidance.
1
Sources
50%
Confidence
Long-term
Relevance
11/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe first SFT stage adopts a "model-aware data construction" method: first synthesizing challenging problems, then adversarially strengthening these problems based on the base model's own successful solving strategies.74% 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.73% 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).72% similarUnverifiedSFT 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.72% similarUnverifiedA new study proposes deriving the RL objective as maximum likelihood fitting to a model-generated target distribution, thereby unifying pretraining, SFT and RL into the same family of objective functions.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1178327API
curl https://kongchang.com/api/v1/knowledge/claims/1178327MCP
get_claim(id=1178327)