cross-dataset

#cross-dataset

Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs

arXiv cs.CL ↗ · 2026-06-15 Cached

This paper evaluates cross-dataset generalization of supervised ML/DL models and prompted LLMs for automatic Bloom's taxonomy classification of assessment questions, finding that LLMs are more robust across diverse educational contexts.

0 favorites 0 likes

#cross-dataset

@vintcessun: Numerical datasets don't even share column names — how can AI retrieve and align across tables? Existing embedding methods fail on heterogeneous tables, and LLMs are at a loss. This problem blocks cross-dataset RAG, algorithm selection, and simulation initialization — without common feature names, similarity matching is guesswork. The paper proposes: compute 20+ statistical descriptors (mean, quantiles, missing rate...) for each table.

X AI KOLs Timeline ↗ · 2026-05-30 Cached

This paper proposes a method for cross-table retrieval and alignment of heterogeneous numerical tabular datasets using statistical descriptors and sentence embeddings, enabling similarity matching and interpretable variable-level correspondence without shared column names.

0 favorites 0 likes

cross-dataset

Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs

Submit Feedback