SOURCE-LINKED INTELLIGENCE

Replacing Training with Memory: Listwise Selection for Text-to-SQL

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise selection, by jointly comparing multiple candidates, has been widely adopted, but fine-tuning listwise selectors is costly. We thus propose a fine-tuning-free listwise selector. We replace two major fine-tuning objectives with inference-time strategies: (1) learning selection criteria as ordering and (2) mitigating positional bias. First, we build reusable structured memories instead of learning selection behavior as model parameters. Given a qu

Read original source ↗ Open in workspace

recordType

paper

region

Global