Unverified50% confidenceFactExact time
Shortcut learning refers to a model relying on spurious features in the data that are correlated with labels but not causal to make judgments, with performance dropping sharply under distribution shift.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedInference methods based on model internal features face a trade-off between false positives and false negatives78% similarUnverifiedSpurious correlation is a common failure mode in machine learning: the model captures features that are statistically correlated with labels but not causally related, and makes predictions based on them.76% similarUnverifiedDue to differing label definitions, a model that achieves high scores on one dataset may see substantially degraded performance on another, making cross-paper numbers not necessarily comparable.76% similarUnverifiedThe quality of tool descriptions directly affects the model's invocation accuracy; vague descriptions or ambiguous parameter naming will cause the model to frequently pass in incorrect parameters.76% similarUnverifiedVector retrieval results are sensitive to the embedding model version, chunking strategy, and index update timing, and the same knowledge may return different rankings in different environments, contradicting the goal of reproducibility.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1153550API
curl https://kongchang.com/api/v1/knowledge/claims/1153550MCP
get_claim(id=1153550)