AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

Jinyang Li, Binyuan Hui, GE QU, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Ruiying Geng, Nan Huo, Xuanhe Zhou, Chenhao Ma and 5 more

NeurIPS 2023 · Large language models › Language, safety and interpretability · approach: LLM unlearning and benchmarks · 87 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add external knowledge evidence to prompt (ablation)GPT-4 · BIRD test EXexecution accuracy: 34.88 -> 54.89Improved
add external knowledge evidence to prompt (ablation)ChatGPT · BIRD dev EXexecution accuracy: 24.05 -> 37.22Improved
add external knowledge evidence to prompt (ablation)T5-3B · BIRD dev EXexecution accuracy: 10.37 -> 23.34Improved
add chain-of-thought promptingChatGPT · BIRD dev EX w/o knowledgeexecution accuracy: 24.05 -> 25.88Improved
add chain-of-thought prompting on top of knowledge evidenceChatGPT · BIRD dev EX w/ knowledgeexecution accuracy: 37.22 -> 36.64Hurt
add DIN-SQL prompting (value sampling, few-shot, self-correction)GPT-4 · BIRD test EX w/ knowledgeexecution accuracy: 54.89 -> 55.90Improved
add DIN-SQL promptingGPT-4 · BIRD test VES w/ knowledgeVES: 60.77 -> 59.44Hurt
two-stage optimization: expert rewrite of correct SQLsChatGPT SQLs · 10 dev examplestime saving: 77.75%Improved
configure indexes in the databaseSQL queries · BIRD efficiency analysistime saving: 87.3%Improved
scale model from T5-Base to T5-3B (w/ knowledge)T5 · BIRD dev EXexecution accuracy: 11.54 -> 23.34Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy