Table-R1 combines region-enhanced supervised fine-tuning with table-aware group relative policy optimization to raise LLM table question answering performance by 14.36 points on average while cutting token consumption by 67.5 percent.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Table-R1: Region-based Reinforcement Learning for Table Understanding
Table-R1 combines region-enhanced supervised fine-tuning with table-aware group relative policy optimization to raise LLM table question answering performance by 14.36 points on average while cutting token consumption by 67.5 percent.