Pith. sign in

REVIEW 17 cited by

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.01943 v1 pith:7ID2LFJT submitted 2024-10-02 cs.LG cs.AIcs.CLcs.DB

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

classification cs.LG cs.AIcs.CLcs.DB
keywords chase-sqlselectioncandidateexecutiontext-to-sqlcandidatesframeworkgeneration
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate generation and selection. CHASE-SQL leverages LLMs' intrinsic knowledge to generate diverse and high-quality SQL candidates using different LLM generators with: (1) a divide-and-conquer method that decomposes complex queries into manageable sub-queries in a single LLM call; (2) chain-of-thought reasoning based on query execution plans, reflecting the steps a database engine takes during execution; and (3) a unique instance-aware synthetic example generation technique, which offers specific few-shot demonstrations tailored to test questions.To identify the best candidate, a selection agent is employed to rank the candidates through pairwise comparisons with a fine-tuned binary-candidates selection LLM. This selection approach has been demonstrated to be more robust over alternatives. The proposed generators-selector framework not only enhances the quality and diversity of SQL queries but also outperforms previous methods. Overall, our proposed CHASE-SQL achieves the state-of-the-art execution accuracy of 73.0% and 73.01% on the test set and development set of the notable BIRD Text-to-SQL dataset benchmark, rendering CHASE-SQL the top submission of the leaderboard (at the time of paper submission).

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Same Data, Different Schemas: Robustness of LLM-based Text-to-SQL

    cs.DB 2026-05 unverdicted novelty 7.0

    A new evaluation framework generates equivalent schemas from an E/R model and shows that LLMs produce SQL queries with different answers across those schemas for fixed questions and data.

  2. Residual Skill Optimization for Text-to-SQL Ensembles

    cs.CL 2026-05 unverdicted novelty 7.0

    Residual skill optimization creates complementary Text-to-SQL agents by training each new skill on prior ensemble failures, yielding accuracy gains on Spider2-Lite and transfer to other dialects and tasks.

  3. CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation

    cs.CL 2026-05 unverdicted novelty 7.0

    CA-SQL achieves 51.72% execution accuracy on the challenging tier of the BIRD benchmark using GPT-4o-mini by scaling exploration breadth according to estimated task difficulty, evolutionary prompt seeding, and candida...

  4. Database Context Compression for Text-to-SQL on Real-World Large Databases

    cs.DB 2026-06 unverdicted novelty 6.0

    DBCC applies SGCF-based offline compression and online purification to shrink database context by up to 100x while raising schema recall and execution accuracy 1.8-1.9% on Spider 2.0 and BIRD.

  5. Bootstrapping Semantic Layer from Execution for Text-to-SQL

    cs.CL 2026-06 unverdicted novelty 6.0

    GATE bootstraps missing semantic groundings for text-to-SQL by testing open hypotheses through partial execution and storing the supported ones as reusable memory entries.

  6. Data-aware candidate selection in NL2SQL translation via small separating instances

    cs.DB 2026-05 unverdicted novelty 6.0

    A selection technique based on separating instances and provenance outperforms baselines for choosing among 2-3 NL2SQL candidates on a BIRD-DEV subset without consistency scores.

  7. FINER-SQL: Boosting Small Language Models for Text-to-SQL

    cs.DB 2026-05 unverdicted novelty 6.0

    FINER-SQL boosts 3B-parameter small language models to 67.73% and 85% execution accuracy on BIRD and Spider benchmarks via dense memory and atomic rewards in group relative policy optimization, matching larger LLMs at...

  8. Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding

    cs.CL 2026-04 unverdicted novelty 6.0

    TeCoD improves Text-to-SQL execution accuracy by up to 36% over in-context learning and cuts latency 2.2x on matched queries by extracting templates from historical pairs and enforcing them with constrained decoding.

  9. AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

    cs.DB 2026-04 unverdicted novelty 6.0

    AV-SQL uses a pipeline of LLM agents to generate intermediate CTE views that decompose complex Text-to-SQL queries, reaching 70.38% execution accuracy on Spider 2.0.

  10. AgentNLQ: A General-Purpose Agent for Natural Language to SQL

    cs.AI 2026-05 unverdicted novelty 5.0

    A multi-agent LLM framework with schema enrichment and business rules achieves 78.1% semantic accuracy on the BIRD NL2SQL benchmark.

  11. Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning

    cs.CL 2026-04 unverdicted novelty 5.0

    APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.

  12. Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs

    cs.CL 2026-04 unverdicted novelty 5.0

    FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.

  13. APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL

    cs.DB 2026-02 conditional novelty 5.0

    An agentic text-to-SQL pipeline using hypothesis-verification exploration achieves 70.7% execution accuracy on BIRD-Dev and 51.0% on Spider 2.0-Snow.

  14. MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL

    cs.CL 2025-11 unverdicted novelty 5.0

    MARS-SQL trains a multi-agent RL system with ReAct-style interaction and generative validation to produce SQL queries, reaching 77.84% execution accuracy on BIRD dev and 89.75% on Spider test.

  15. XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL

    cs.CL 2025-07 unverdicted novelty 5.0

    XiYan-SQL achieves SOTA Text-to-SQL accuracy by combining schema filtering, a multi-generator ensemble fine-tuned on varied SQL formats, and a selection model.

  16. CHESS: Contextual Harnessing for Efficient SQL Synthesis

    cs.LG 2024-05 conditional novelty 5.0

    CHESS deploys four LLM agents to retrieve information, prune schemas, generate refined SQL candidates, and validate via unit tests, reporting up to 71.10% accuracy on BIRD with 83% fewer calls than leading proprietary...

  17. When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables

    cs.CL 2025-09 unverdicted novelty 4.0

    EnoTab is a dual denoising framework for TableQA that performs evidence-based question denoising via semantic unit decomposition and evidence tree-guided table pruning with post-order rollback to improve performance o...