Reproduce “Knowledge Base Construction for Knowledge-Augmented Text-to-SQL” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jinheon Baek, Horst Samulowitz, Oktie Hassanzadeh, Dharmashankar Subramanian, Sola Shirai, Alfio Gliozzo, Debarun Bhattacharjya
KAT-SQL builds a reusable, schema-aware knowledge base from question–schema–knowledge examples, retrieves entries relevant to a new question, refines them, and uses them to generate SQL. On BIRD Non-Overlap, it achieves 41.07 execution accuracy with Llama-3 70B, versus 24.64 for DELLM; human-curated Oracle Knowledge reaches 49.41, showing the approach improves results in tested settings but does not close that gap.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.