Unverified50% confidenceFactExact time
Linear probes perform well on the training distribution, but their performance often drops sharply when facing out-of-distribution (OOD) samples.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedReinforcement learning in the post-training stage can improve answer accuracy on both in-distribution and out-of-distribution tasks, but does not consistently improve the validity of reasoning traces.73% similarUnverified针对特定工具做专项强化训练的副作用是对非训练分布工具的泛化能力下降，学术上称为分布外泛化失败72% similarUnverified诊断训练瓶颈的核心效率差异来自于是否提前建立了性能基线（baseline），如已知模型健康状态下的MFU则可快速发现偏离72% similarUnverifiedA 2017 study by Keskar et al. showed that large-batch training tends to converge to sharp minima corresponding to worse generalization, while small-batch training tends toward flat minima.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/899108API
curl https://kongchang.com/api/v1/knowledge/claims/899108MCP
get_claim(id=899108)