retrieval · retrieve-clause-level-knowledge-database-s-sql-query TEC-0177 · proposed

Retrieve clause-level knowledge from a database's SQL query

Parse past SQL into five categories of clause-level fragments, describe each in natural language, retrieve by query- and component-level embedding similarity, then LLM-rerank before prepending to an existing few-shot text-to-SQL prompt.

Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.

Parse past SQL into five categories of clause-level fragments, describe each in natural language, retrieve by query- and component-level embedding similarity, then LLM-rerank before prepending to an existing few-shot text-to-SQL prompt. Filed by the drafting stage from BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations (2608.29345) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Execution accuracy on BIRD-History (1,393 tasks, 11 databases) against each pipeline's own retriever: DAIL-SQL 40.78 to 51.33, OpenSearch-SQL 59.15 to 60.95, N-rep 54.49 to 57.79, CodeS-7B 12.92 to 18.95; retrieval F1 49.77 vs 28.69-34.88 for baseline retrievers; shot-count sweep shows EX peaking at 4 shots (61.31) with precision falling from 57.95 to 35.53 as recall rises to 83.07.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Writing a reusable locator: regex, SQL, XPath

Does it work?

nothing measured0 supporting · 0 contesting sources

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.

No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.

Code

No repository linked yet. Contribute one.

Sources

Either way, bring evidence: a link, or what you saw.

Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.