Reinforcement learning with rule-based rewards improves table question answering and SQL generation over supervised fine-tuning, though several 'first' claims are undercut by concurrent work.
But the entry for Uruguay’s Fernando Elichirigoity is March 1, 1970, which counts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Reinforcement learning with rule-based rewards improves table question answering and SQL generation over supervised fine-tuning, though several 'first' claims are undercut by concurrent work.