Unverified50% confidenceBenchmarkExact time
Under the primary experimental setting, GraftOOD leads in nine out of ten metrics in a horizontal comparison among three example-augmentation methods.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
Unverified少样本学习中，3个高质量、覆盖边界情况的示例往往优于10个平庸示例，且最后一个示例对模型的影响权重通常最大73% similarUnverifiedOn the strongest models, the differences between experimental groups fall within confidence intervals, and researchers characterized the results as directional patterns and soundness properties rather than proven performance lower bounds68% similarUnverifiedThe generator LLM, probe model, and prompt verbosity together contribute less than 10% of the variance.67% similarUnverifiedThese AI personas were able to correctly follow the characteristic settings assigned to them in 91.5% of trials in the experiments.66% similarUnverifiedIn few-shot prompting, the quality of examples is generally more important than quantity, and 1–3 highly representative examples often outperform 10 examples of uneven quality65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001545API
curl https://kongchang.com/api/v1/knowledge/claims/1001545MCP
get_claim(id=1001545)