TabSQLify (col+row)

Reported on 3 benchmarks across 3 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Question AnsweringonWikiTableQuestions
Accuracy (Test)· 2024-04-15
64.7
SOTA
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition arXiv:2404.10150
Semantic ParsingonWikiTableQuestions
Accuracy (Test)· 2024-04-15
64.7
best: 80.8 (ARTEMIS-DA)
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition arXiv:2404.10150
Table-based Fact VerificationonTabFact
Test· 2024-04-15
79.5
best: 93.1 (ARTEMIS-DA)
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition arXiv:2404.10150