A schema-summarization and code-generation pipeline, TableReasoner, won first place on both SemEval-2025 Task 8 subtasks, with 93.87% and 91.76% accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TableReasoner: Advancing Table Reasoning Framework with Large Language Models
A schema-summarization and code-generation pipeline, TableReasoner, won first place on both SemEval-2025 Task 8 subtasks, with 93.87% and 91.76% accuracy.