Unverified50% confidenceOpinionExact time
模型能力高度依赖训练数据的分布，法律文本充足而空间推理题的文本化表示相对稀少
1
Sources
50%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAlignment 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.74% similarUnverifiedSimply stacking parameters without sufficient training data results in a model that is large but not capable; a leap in parameters must be accompanied by a proportionally expanded training corpus and computing power to realize capability gains.73% similarUnverified模型权重是一种高度压缩的统计表征，并非训练文本的直接存储，单凭权重文件无法还原原始训练样本72% similarUnverifiedOpenAI在InstructGPT论文中证明，少量高质量人类偏好数据对模型对齐的贡献远超大规模无监督训练72% similarUnverifiedUsing nonsense words as prompts can guide the model into regions of the latent space that are less frequently activated in training data, thereby producing more diverse results.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/804700API
curl https://kongchang.com/api/v1/knowledge/claims/804700MCP
get_claim(id=804700)