Unverified50% confidenceSolutionExact time
若训练集能充分覆盖推理时可能出现的工具类型和参数组合，小模型同样能学到可靠的格式生成能力，而不必依赖大模型的深层语义推理
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
UnverifiedThe Skills paradigm uses the large language model itself to simultaneously perform intent understanding, slot filling, and parameter structuring, achieving zero-shot intent routing without requiring additional training data.79% similarUnverified少样本学习通过在Prompt中提供2-5个示例帮助模型快速理解输出格式和风格要求79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/518117API
curl https://kongchang.com/api/v1/knowledge/claims/518117MCP
get_claim(id=518117)