A table-tuned Gemma model with a pre-filled KV cache produces context-aware row embeddings that improve tabular predictors, especially with little training data.
LIFT: Language-interfaced fine-tuning for non-language machine learning tasks.Advances in Neural Information Processing Systems, 35:11763–11784, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Enhancing Tabular Learners with Context-Aware Semantic Embeddings
A table-tuned Gemma model with a pre-filled KV cache produces context-aware row embeddings that improve tabular predictors, especially with little training data.