FINER-SQL boosts 3B-parameter small language models to 67.73% and 85% execution accuracy on BIRD and Spider benchmarks via dense memory and atomic rewards in group relative policy optimization, matching larger LLMs at lower latency.
Direct preference optimization: Your language model is secretly a reward model,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FINER-SQL: Boosting Small Language Models for Text-to-SQL
FINER-SQL boosts 3B-parameter small language models to 67.73% and 85% execution accuracy on BIRD and Spider benchmarks via dense memory and atomic rewards in group relative policy optimization, matching larger LLMs at lower latency.