Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning

arXiv:2402.12554v1 Announce Type: new
Abstract: 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 …

abstract arxiv bilingual chinese cs.cl databases dataset domains english human queries questions reasoning sql sql queries text text-to-sql type