Unverified50% confidenceConceptExact time
Compositional generalization refers to a model's ability to understand and generate novel combinations unseen in training, for example understanding "the cat chases the ball" after learning "the cat chases the mouse" and "the dog chases the ball".
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCompositional Generalization requires a model to freely combine independently learned concepts to generate new combinations that never appeared in the training set.75% similarUnverifiedGeneralization refers to a model's performance on unseen new data.70% similarUnverifiedThe academic community typically uses compositional generalization to measure genuine reasoning ability.70% similarUnverifiedThe trend revealed by Latent Compaction is that static components in the inference process can dynamically adapt to the input through test-time training.65% similarUnverifiedThe term "regularization" is borrowed from machine learning, referring to the addition of a penalty term during model training to prevent overfitting.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1082779API
curl https://kongchang.com/api/v1/knowledge/claims/1082779MCP
get_claim(id=1082779)