Code

SQL-PaLM

First page

Paper summary

An LLM-based Text-to-SQL system built on PaLM-2.

Ask this paper

Key points

SOTA in both settings: Achieves state-of-the-art on Spider benchmark in both in-context learning and fine-tuning settings.

Beats GPT-4 few-shot: Few-shot SQL-PaLM outperforms few-shot GPT-4 by 9.9% using a simple prompting approach.

Improves on fine-tuned baselines: The few-shot setting even outperforms the previous fine-tuned SOTA by 3.8%.

Text-to-SQL direction: Part of the Text-to-SQL surge that led to production NL-to-SQL systems in analytics platforms through 2024.

Every Monday