Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning
This dataset provides a challenging benchmark for text-to-SQL research, addressing complex reasoning gaps in existing datasets.
The authors introduced Archer, a bilingual text-to-SQL dataset designed to test complex reasoning like arithmetic and commonsense, and found that a top model from the Spider leaderboard achieved only 6.73% execution accuracy on it.
We present Archer, a challenging bilingual text-to-SQL dataset specific to complex reasoning, including arithmetic, commonsense and hypothetical reasoning. It contains 1,042 English questions and 1,042 Chinese questions, along with 521 unique SQL queries, covering 20 English databases across 20 domains. Notably, this dataset demonstrates a significantly higher level of complexity compared to existing publicly available datasets. Our evaluation shows that Archer challenges the capabilities of current state-of-the-art models, with a high-ranked model on the Spider leaderboard achieving only 6.73% execution accuracy on Archer test set. Thus, Archer presents a significant challenge for future research in this field.