all AI news
CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL. (arXiv:2311.01173v1 [cs.CL])
cs.CL updates on arXiv.org arxiv.org
Existing Text-to-SQL generators require the entire schema to be encoded with
the user text. This is expensive or impractical for large databases with tens
of thousands of columns. Standard dense retrieval techniques are inadequate for
schema subsetting of a large structured database, where the correct semantics
of retrieval demands that we rank sets of schema elements rather than
individual elements. In response, we propose a two-stage process for effective
coverage during retrieval. First, we instruct an LLM to hallucinate a …
arxiv collective database databases hallucination retrieval schema semantics sql standard text text-to-sql