The DOI matches its Crossref record; the references it cites are not checked yet.
Optimizing Reasoning for Text-to-SQL with Execution Feedback
Open accessAbstract
Text-to-SQL demands precise reasoning to convert natural language questions into structured queries.While large language models (LLMs) excel in many reasoning tasks, their ability to leverage Chain-of-Thought (CoT) reasoning for text-to-SQL remains underexplored.We identify critical limitations: zero-shot CoT offers minimal gains, and Direct Preference Optimization (DPO) applied without CoT yields marginal improvements.We propose ExCoT-DPO, a novel framework that iteratively optimizes open-source LLMs by combining CoT reasoning with off-policy and on-policy DPO, relying solely on execution accuracy as feedback.This approach eliminates the need for reward models or human-annotated preferences.Our experimental results demonstrate significant performance gains: ExCoT-DPO improves execution accuracy on BIRD from 57.37% to 68.51% and on Spider from 78.81% to 86.59% for LLaMA-3 70B, with Qwen-2.5-Coderdemonstrating similar improvements.Our best model achieves state-of-the-art performance in the single-model setting on both BIRD and Spider datasets, notably achieving 68.53% on the BIRD test set. 1
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
The citation lists haven’t been fetched yet
References 23 · Cited by 8
Metadata
- Authors
- Zhai, B., Xu, C., He, Y., & Yao, Z.
- Affiliations
- Snowflake Inc. (United States) (US)
- Venue
- Findings of the Association for Computational Linguistics: ACL 2025
- Published
- 2025
- Pages
- 19206-19218
- OpenAlex
- W4412887891
- Cited by
- 8
- References
- 23
- Citations by year
- 2026: 7 · 2025: 1
- FWCI
- 5.62
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: ACL (Findings of ACL) (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- text-to-SQL, chain-of-thought reasoning, direct preference optimization, execution feedback, large language models, query generation, Spider dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
