Unverified50% confidenceOpinionExact time
The generalization discussed in this experiment is closer to out-of-distribution reasoning, i.e., the training data distribution does not contain weight-function paired text.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
Unverified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79% similarUnverifiedExternal scheduling at inference time and internally learned capabilities during training differ in generalization performance and controllability.76% similarUnverifiedGlobal classification is not suitable for local tampering detection, and in small-data scenarios, self-supervised pre-training and domain priors are often more effective than larger models.75% similarUnverifiedReinforcement 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.75% similarUnverifiedResearch shows that even when a distribution gap exists between synthetic and real data, as long as the pre-trained model has learned sufficiently generalizable anatomical feature representations, fine-tuning with a small amount of real data is sufficient to bridge this gap.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134436API
curl https://kongchang.com/api/v1/knowledge/claims/1134436MCP
get_claim(id=1134436)