Unverified50% confidenceFactExact time
SFT (supervised fine-tuning) using causal language modeling in the post-training stage takes the form of user tasks with chat templates applied, available tool sets, and tool response payloads from the environment.
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe SFT training data format contains three roles: system prompt, user (user input), and assistant (model response).79% similarUnverifiedFunction Calling能力需要在监督微调（SFT）阶段喂入高质量的工具调用对话数据才能获得78% similarUnverifiedThe Instruct Models open-sourced by major companies are versions that have acquired conversational capabilities after the SFT stage.74% similarUnverified工具调用的本质是模型通过SFT和RLHF学会按特定格式输出函数调用请求，真正的执行由外部运行时完成72% similarUnverified该工具提供Token用量查看功能，用户需自行配置对话模型和生图模型69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/928819API
curl https://kongchang.com/api/v1/knowledge/claims/928819MCP
get_claim(id=928819)