← Back to all news
arXiv AI By Haoyuan Ma, Hengwei Liu, Linjuan Wu, Yongliang Shen, Weiming Lu

LIMIT: Less Is More for Instruction Tuning in Text-to-SQL

Read the original on arXiv AI →

LIMIT (Less Is More for Instruction Tuning in Text-to-SQL) challenges the belief that large instruction corpora are necessary for effective Text-to-SQL models. The framework uses a four‑stage data‑centric process—difficulty‑aware filtering, chain‑of‑thought synthesis, LLM‑as‑judge quality scoring, and genetic algorithm optimization—to select a compact set of examples that still achieve full schema coverage. On the BIRD and Spider benchmarks, LIMIT’s 796 and 863 samples enable Qwen3‑8B to reach 69.1% and 88.9% execution accuracy, outperforming methods trained on twenty times more data and setting a new state‑of‑the‑art for open‑source approaches.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 2

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

The paper proposes a fine‑tuning‑free listwise selector for Text‑to‑SQL systems that replaces traditional learning objectives with inference‑time strategies. It introduces reusable structured memories (MaP‑SQL) that encode mappings from natural language to schema elements, SQL operations, and expected outputs, and uses these memories to evaluate candidate queries. To reduce positional bias, the method aggregates rankings across multiple input permutations, optimizing inference cost through execution results and pointwise scoring. The approach achieves higher selection accuracy, fewer unnecessary comparisons, and outperforms the prior state‑of‑the‑art R^3‑SQL on the BIRD‑dev benchmark while using fewer tokens.

By Yeonseok Jeong, Soyoung Yoon, Seongjun Lee, Seung-won Hwang
llmsfine-tuningbenchmarkssafetydata-engineering
More like this →
arXiv AI
Jul 24

EvoSQL: Memory-Augmented Critic-Generator Co-Evolution for Text-to-SQL

arXiv:2607. 20489v1 Announce Type: new Abstract: Text-to-SQL has advanced rapidly with large language models, but complex database queries still require reasoning beyond one-shot generation, including multi-step decomposition, execution-based diagnosis, and targeted correction.

By Jiawei Zhou, Jianwei Wang, Chenyu Zhou, Chaojian Shi, Ming Dong, Kai Wang
llmsfine-tuningefficiencydata-engineering
More like this →