Unverified50% confidenceFactExact time
Function Calling能力通过SFT阶段构造大量工具调用示例数据获得，结合RLHF优化工具选择准确性
1
Sources
50%
Confidence
Long-term
Relevance
7/21/2026
First Seen
Sources
Related Claims
Unverified指令跟随能力依赖于监督微调（SFT）阶段和RLHF阶段的偏好对齐优化73% similarUnverifiedFunction Calling的可靠性高度依赖RLHF对调用时机的精确校准，模型需在训练阶段学习何时调用工具的判断边界65% similarUnverified函数调用的可靠性高度依赖于工具描述的质量，清晰的参数说明和使用示例往往比模型本身能力更能决定工具调用成功率60% similarUnverifiedSafety alignment is typically achieved through stages such as supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF); more recent and efficient methods such as direct preference optimization (DPO) have emerged, with alignment goals summarized as the 3H principle: helpful, honest, and harmless.60% similarUnverifiedThe quality of tool descriptions directly affects the accuracy of model invocation.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/581958API
curl https://kongchang.com/api/v1/knowledge/claims/581958MCP
get_claim(id=581958)