Verified75% confidenceFactExact time
In-context learning was first observed in large language models, and its capability fundamentally stems from the diversity of pretraining data.
3
Sources
75%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Related Claims
UnverifiedMainstream large language models and image recognition models rely on massive amounts of training data.79% similarVerified大语言模型的预训练阶段本质上属于自监督学习，是一种特殊的非监督学习，模型通过预测下一个词来从海量文本中自动学习语言规律79% similarUnverifiedUneven distribution of training corpus is the root cause of deviations in model capability, and a large model's code generation ability for a language depends heavily on the volume, diversity and quality of that language's code in the pre-training data.78% similarUnverifiedExisting research shows that large language models exhibit a clear memory preference when parametric knowledge conflicts with retrieved evidence, tending to rely on knowledge acquired during training.78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/491522API
curl https://kongchang.com/api/v1/knowledge/claims/491522MCP
get_claim(id=491522)