Unverified50% confidenceEventExact time
A semi-synthetic study based on real electronic health record covariates shows that a globally trained policy misgeneralizes on a high-risk subgroup, while FDR control limits the number of harmful treatments that the policy would otherwise have administered.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOverfitting refers to the phenomenon where a model performs extremely well on the training set but generalizes poorly to new data, and this risk is especially prominent in pharmacy datasets with relatively small sample sizes.78% similarUnverifiedResearch on SelectPFN proved a negative result: training in the average case does not automatically translate into frequentist guarantees under a fixed ground truth, so controlling the false discovery rate on any given dataset requires additional mechanisms.72% similarVerifiedTraining data poisoning can implant persistent backdoors at the model weight level, posing far greater risks than application-layer jailbreaks, but the implementation threshold is higher and typically requires control over the training pipeline.72% similarVerifiedAlignment training optimizes the model's statistical behavior in known scenarios rather than establishing formally verifiable security boundaries, and may fail when faced with rare instruction combinations or role-playing frameworks outside the training distribution.71% similarUnverifiedStrictly controlling the proportion of synthetic data in the training set to prevent it from becoming dominant is one response strategy in mixed training approaches.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1068340API
curl https://kongchang.com/api/v1/knowledge/claims/1068340MCP
get_claim(id=1068340)