selecting-among-multiple-generated-sql-candidates-listwise-selector-given CLM-0482For selecting among multiple generated SQL candidates, a listwise selector given retrieved structured selection criteria distilled from training question-SQL pairs, with candidates grouped by execution result and permuted only within groups, reaches higher execution accuracy than pointwise, pairwise and multi-selector baselines on the same candidate pools while using far fewer selector calls and tokens.
Capability: Writing a reusable locator: regex, SQL, XPath
Observed on
Text-to-SQL candidate selection with 8 or 32 candidates from fixed generators, BIRD-dev, Spider-test and EHRSQL, selector Qwen3-Coder-30B-A3B-Instruct; assumes a labelled training .
Sources
- Validated by: Execution accuracy, selector calls and input tokens per query against greedy, majority voting, pointwise (Contextual-RM-32B), pairwise (CHASE-SQL style) and R3-SQL on the same candidate sets: 73.08 vs 71.97 for R3-SQL on BIRD-dev at n=32, +2.02 over pairwise, 2.92x fewer tokens; ablations drop 0.55 (no memory) and 0.32 (no permutation); order-consistency rises 18.98 -> 23.04 (global shuffle) -> 29.04 (group-based) -> 33.17 (with tie-break).. [truncated]
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- For instruction tuning an 8B open model on text-to-SQL, a curated set of under 900 examples selected to cover every table in the target schemas and score well on question-SQL alignment reaches higher execution accuracy than pipelines trained on tens of thousands to millions of samples, and dropping the schema-coverage term from the selection objective costs more accuracy than dropping any single quality term.Writing a reusable locator: regex, SQL, XPath · reviewed by AI
- On text-to-SQL questions that are underspecified with respect to the schema, retrieving clause-level fragments (conditions, joins, calculations, groupings, output specs) from a database's own past successful SQL queries and prepending them to existing few-shot pipelines raises execution accuracy across four different pipelines, but the gain saturates and can reverse once too many candidates are retrieved, because high recall with low precision lets the generator pick a plausible-but-wrong pattern.Writing a reusable locator: regex, SQL, XPath · reviewed by AI
- For response-level hallucination detection in retrieval-augmented settings, having the model first convert the reference documents into a relational SQL database and then check the response against SELECT query results raises precision and macro F1 over zero-shot direct prediction, over atomic-claim decomposition, and over flat JSON key-value extraction, without any task-specific fine-tuning.Stating false facts confidently · reviewed by AI
- When post-training a 7-8B open model for text-to-SQL with a fixed budget of synthetic examples drawn from a large external pool, selecting examples whose schema-independent SQL skeletons are farthest from those already in the seed set (greedy K-center) rather than sampling randomly from the same pool yields a small in-domain gain and a larger cross-domain one (BIRD dev 64.9 vs 64.4, Spider Test 85.3 vs 83.4, Science Benchmark 53.9 vs 49.8).Writing a reusable locator: regex, SQL, XPath · reviewed by AI
- On natural-language-to-SQL synthesis over multi-table databases, a model's accuracy overstates its ability whenever the same database or the same query appears in both training and test: splitting by database rather than by example cut the best system's exact-match accuracy from 33.0% to 12.4%, and accuracy falls further as the target database has more foreign keys.Writing a reusable locator: regex, SQL, XPath · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: On the same candidate pools, a listwise selector with global permutation and no retrieved memories matches or beats this pipeline's execution accuracy and order-consistency, or the reported gains disappear when the pairwise and R3-SQL baselines are given equal token budgets.