StatBot.Swiss: Bilingual Open Data Exploration in Natural Language
This addresses the problem of evaluating Text-to-SQL systems in non-English languages for researchers and practitioners, though it is incremental as it extends existing benchmarks to a bilingual context.
The authors tackled the lack of bilingual benchmarks for Text-to-SQL systems by releasing the StatBot.Swiss dataset, containing 455 natural language/SQL pairs in English and German, and found that current LLMs like GPT-3.5-Turbo and mixtral-8x7b-instruct struggle to generalize well on this dataset.
The potential for improvements brought by Large Language Models (LLMs) in Text-to-SQL systems is mostly assessed on monolingual English datasets. However, LLMs' performance for other languages remains vastly unexplored. In this work, we release the StatBot.Swiss dataset, the first bilingual benchmark for evaluating Text-to-SQL systems based on real-world applications. The StatBot.Swiss dataset contains 455 natural language/SQL-pairs over 35 big databases with varying level of complexity for both English and German. We evaluate the performance of state-of-the-art LLMs such as GPT-3.5-Turbo and mixtral-8x7b-instruct for the Text-to-SQL translation task using an in-context learning approach. Our experimental analysis illustrates that current LLMs struggle to generalize well in generating SQL queries on our novel bilingual dataset.