Unverified50% confidenceFactExact time
Weak supervision employs a method in which domain experts write Labeling Functions, and the system synthesizes these rules through probabilistic models to generate soft labels with confidence scores.
1
Sources
50%
Confidence
Long-term
Relevance
9/22/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedKnowledge distillation technology enables small models to extract a considerable proportion of capability from large models, undermining the validity of fixed compute thresholds as a proxy metric for capability.67% similarUnverified贝叶斯优化基于概率代理模型（通常为高斯过程）建模历史实验结果，在探索与利用之间智能权衡，通常能以更少实验次数找到接近最优的参数配置67% similarUnverifiedPrompt engineering techniques (chain-of-thought, few-shot examples, role assignment, structured output, etc.) are in essence methods of narrowing the model's output distribution through additional linguistic constraints, guiding it toward a probability range closer to the user's intent.66% similarUnverified简单的参数提取、格式转换类任务使用成本较低的小模型即可完成，复杂的测试逻辑推理、异常根因分析才需要调用旗舰模型66% similarUnverifiedWhen fine-tuning embedding models, hard negatives (such as positions in the same domain but at different levels) should be used instead of random negatives, in order to learn more fine-grained semantic differences.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942106API
curl https://kongchang.com/api/v1/knowledge/claims/942106MCP
get_claim(id=942106)