Unverified50% confidenceCautionExact time
如果预训练模型主要在西欧或北美城市数据上训练，直接应用于东欧城市可能因建筑风格差异出现漏检或误检
1
Sources
50%
Confidence
Long-term
Relevance
8/11/2026
First Seen
Sources
Related Claims
Unverified若模型在训练过程中意识到自身会被审计，理论上存在通过学习规避审计特征来通过检测的可能，这一风险在具有强化学习背景的模型中尤为值得关注61% similarUnverifiedEarly local objective training methods such as layer-wise pretraining typically underperformed compared to end-to-end training.61% similarUnverifiedSafety classifiers are typically fine-tuned from pre-trained language models such as BERT and RoBERTa, or use specially trained lightweight discriminative models.58% similarUnverifiedMainstream benchmark problems have been widely discussed on the internet, and models' training data may contain memorization of these problems, causing benchmark scores to overestimate the models' capabilities on truly unseen tasks58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/731935API
curl https://kongchang.com/api/v1/knowledge/claims/731935MCP
get_claim(id=731935)