LDI introduces localized LLM-based imputation for text-rich tables by selecting compact relevant subsets of attributes and tuples per missing value, reporting up to 8% accuracy gains over prior methods.
Large language models are few (1)-shot table reasoners
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
TaNOS decouples table semantics from numerical structure via anonymization, sketches, and program-first self-supervision, yielding 80.13% FinQA accuracy with 10% data and near-zero cross-domain gap versus over 10pp for standard fine-tuning.
citing papers explorer
-
LDI: Localized Data Imputation for Text-Rich Tables
LDI introduces localized LLM-based imputation for text-rich tables by selecting compact relevant subsets of attributes and tuples per missing value, reporting up to 8% accuracy gains over prior methods.
-
Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning
TaNOS decouples table semantics from numerical structure via anonymization, sketches, and program-first self-supervision, yielding 80.13% FinQA accuracy with 10% data and near-zero cross-domain gap versus over 10pp for standard fine-tuning.