Pith. sign in

REVIEW 39 cited by

C3: Zero-shot Text-to-SQL with ChatGPT

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2307.07306 v1 pith:CGYV3CD7 submitted 2023-07-14 cs.CL cs.AI

Xuemei Dong , Chao Zhang , Yuhang Ge , Yuren Mao , Yunjun Gao , lu Chen , Jinshu Lin , Dongfang Lou This is my paper · ORCID
classification cs.CLcs.AI
keywords text-to-sqlzero-shotmethodmodeloutputspideraccuracyachieves
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper proposes a ChatGPT-based zero-shot Text-to-SQL method, dubbed C3, which achieves 82.3\% in terms of execution accuracy on the holdout test set of Spider and becomes the state-of-the-art zero-shot Text-to-SQL method on the Spider Challenge. C3 consists of three key components: Clear Prompting (CP), Calibration with Hints (CH), and Consistent Output (CO), which are corresponding to the model input, model bias and model output respectively. It provides a systematic treatment for zero-shot Text-to-SQL. Extensive experiments have been conducted to verify the effectiveness and efficiency of our proposed method.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 39 Pith papers

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

  1. SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL

    cs.DB 2026-08 conditional novelty 7.0 of 10

    SafeQL, an in-DBMS search-based refinement framework, fixes LLM-generated SQL errors by guided AST-level repair, improving execution accuracy by up to 5.8% and cutting token usage up to 15x.

  2. Text-to-SQL Oriented to the Process Mining Domain: A PT-EN Dataset for Query Translation

    cs.IR 2025-08 conditional novelty 7.0 of 10

    text-2-SQL-4-PM is a bilingual benchmark with 1,655 human utterances and 205 gold SQL statements for text-to-SQL in process mining.

  3. DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation

    cs.DB 2026-08 conditional novelty 6.0 of 10

    A non-fine-tuning text-to-SQL pipeline with deep schema disambiguation notes, database-agnostic correction rules mined from training data, and dependency-tree-guided SQL generation reports state-of-the-art execution a...

  4. From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQL

    cs.CL 2026-08 accept novelty 6.0 of 10

    Storing verified corrected text-to-SQL queries in a per-database bank improves held-out first-attempt accuracy by 4.34 percentage points, capturing 44.4% of on-demand repair headroom.

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

    cs.AI 2026-06 conditional novelty 6.0 of 10

    A generator-critic co-evolution loop with per-question memory lifts Text-to-SQL execution accuracy by up to +9.19 points over majority-vote baselines on Spider and BIRD.

  6. ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement

    cs.CL 2026-03 conditional novelty 6.0 of 10

    A fine-tuned model with special error tokens detects SQL mistakes and guides LLMs to fix them, raising execution accuracy on BIRD from 55.87% to 66.23% and on Spider from 75.44% to 86.94% over GPT-4o.

  7. SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    SEED automatically generates evidence from database schemas, descriptions, and sampled values, improving text-to-SQL accuracy in no-evidence settings.

  8. RAISE: Reasoning Agent for Interactive SQL Exploration

    cs.AI 2025-06 conditional novelty 6.0 of 10

    An interactive reasoning agent that explores databases with live queries raises text-to-SQL execution accuracy from 44.8% to 56.5% and achieves 81.8% best-of-N coverage on BIRD.

  9. Knowledge Base Construction for Knowledge-Augmented Text-to-SQL

    cs.CL 2025-05 conditional novelty 6.0 of 10

    KAT-SQL constructs a reusable knowledge base for text-to-SQL by expanding training data with LLM-generated knowledge and retrieving/refining the best entries for each query.

  10. Automatic Metadata Extraction for Text-to-SQL

    cs.DB 2025-05 conditional novelty 6.0 of 10

    LLM-generated summaries of database profiling statistics outperform human-written metadata for text-to-SQL on BIRD, and a SQL-generation-based schema linker adds further gains.

  11. ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Execution-driven bootstrapping, where a model generates SQL, executes it, and keeps only queries that run, lets a 7B model outperform GPT-4o on PostgreSQL, MySQL, and Oracle text-to-SQL benchmarks.

  12. ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL

    cs.CL 2025-05 conditional novelty 6.0 of 10

    An execution-aware reinforcement learning framework that interleaves intermediate SQL execution into the reasoning path improves text-to-SQL accuracy on Spider and BIRD at the 7B scale.

  13. Text-to-TrajVis: Enabling Trajectory Data Visualizations from Natural Language Questions

    cs.CL 2025-04 conditional novelty 6.0 of 10

    TrajVL is a new 18,140-pair benchmark that translates natural language questions about GPS trajectories into a custom trajectory visualization language.

  14. SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation

    cs.DB 2025-04 conditional novelty 6.0 of 10

    A three-team multi-agent framework (GPT-4o exploration, lightweight local expansion, adaptive management) generates over 300,000 diverse SQL queries for under $200 and improves downstream text-to-SQL and clustering baselines.

  15. Extractive Schema Linking for Text-to-SQL

    cs.DB 2025-01 conditional novelty 6.0 of 10

    Extractive schema linking with decoder-only LLMs beats generative and cross-encoder baselines on Spider and BIRD while running more than twenty times faster than generative linking.

  16. Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL

    cs.DB 2025-01 conditional novelty 6.0 of 10

    Feeding Gemini 1.5 a long context with all tables, sample column values, hints, and many synthetic examples reaches 67.41% execution accuracy on BIRD dev without fine-tuning or self-consistency.

  17. Learning When to Reason for Text-to-SQL via SFT and DPO

    cs.CL 2026-06 conditional novelty 5.0 of 10

    A training pipeline that teaches a text-to-SQL model to skip chain-of-thought reasoning on easy queries preserves accuracy while reducing inference tokens and latency.

  18. Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL

    cs.AI 2026-06 conditional novelty 5.0 of 10

    Live schema grounding against Oracle's catalog plus alias/column validation lifts execution-grounded NL2SQL correctness from 2.2% to 62.6% on 500 TPC-H questions.

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

    cs.DB 2026-02 conditional novelty 5.0 of 10

    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.

  20. X-SQL: Expert Schema Linking and Understanding of Text-to-SQL with Multi-LLMs

    cs.LG 2025-09 conditional novelty 5.0 of 10

    X-SQL, an expert schema-linking and schema-understanding framework, achieves 84.9% and 82.5% execution accuracy on Spider-Dev and Spider-Test using open-source LLMs.

  21. Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages

    cs.CL 2025-06 conditional novelty 5.0 of 10

    Generating Python programs as intermediate guidance before SQL, then voting on Python execution results to select the fastest matching SQL, improves text-to-SQL execution accuracy and efficiency on BIRD and Archer.

  22. Effectiveness of Prompt Optimization in NL2SQL Systems

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Iterative prompt optimization with an LLM proposer improves NL2SQL accuracy and prompt compactness on BIRD dev, and a latency-aware variant reduces worst-case SQL execution time.

  23. CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning

    cs.CL 2025-05 conditional novelty 5.0 of 10

    CSC-SQL adds a merge-revision stage and RL fine-tuning to self-consistency, improving execution accuracy on BIRD and Spider text-to-SQL benchmarks.

  24. Rationalization Models for Text-to-SQL

    cs.CL 2025-02 conditional novelty 5.0 of 10

    A pipeline that generates database-validated chain-of-thought SQL rationales from a 70B teacher, and fine-tunes an 8B student on the longest rationales, improves BIRD dev execution accuracy to 67.41%.

  25. A Plug-and-Play Natural Language Rewriter for Natural Language to SQL

    cs.DB 2024-12 conditional novelty 5.0 of 10

    A multi-agent LLM module that checks, reflects on, and rewrites flawed questions yields small average execution-accuracy gains (1.6% Spider, 2.0% BIRD) on NL2SQL dev sets.

  26. Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL

    cs.CL 2024-12 conditional novelty 5.0 of 10

    Solid-SQL reports higher SQL execution accuracy on Spider, Bird, and perturbed variants by strengthening schema linking and example retrieval before LLM-based SQL generation.

  27. ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL

    cs.CL 2024-12 conditional novelty 5.0 of 10

    Multitask supervised fine-tuning plus collaborative prompting on schema linking, noise correction, and continuation writing lifts open-source LLM Text2SQL accuracy on SPIDER and BIRD.

  28. Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models

    cs.DB 2024-12 conditional novelty 5.0 of 10

    TiInsight automates cross-domain data exploration by summarizing database schemas with LLMs, generating SQL, and recommending charts, achieving 86.3% execution accuracy on Spider and state-of-the-art results on Bird.

  29. Towards Agentic Schema Refinement

    cs.DB 2024-11 conditional novelty 5.0 of 10

    A multi-agent LLM workflow automatically defines small database views as a semantic layer, validated only by structural statistics on two datasets.

  30. CHS-SQL: A Text-to-SQL approach based on Confidence-Guided Heuristic Search Schema Linking process

    cs.AI 2026-06 conditional novelty 4.0 of 10

    CHS-SQL combines beam search with model-internal-confidence filtering in schema linking to improve small-model text-to-SQL accuracy on Spider and BIRD.

  31. Text to Query Plans for Question Answering on Large Tables

    cs.DB 2025-08 conditional novelty 4.0 of 10

    A ReAct-style LLM agent converts natural-language questions into query plans over DataFrame operators, using a three-level column-cluster-table vector index to handle tables with over 8,000 columns.

  32. Confidence Estimation for Text-to-SQL in Large Language Models

    cs.CL 2025-08 unverdicted novelty 4.0 of 10

    Consistency-based methods are the most reliable confidence signal for text-to-SQL in black-box LLMs, and executing queries against a database adds a useful correctness signal.

  33. SLM-SQL: An Exploration of Small Language Models for Text-to-SQL

    cs.CL 2025-07 conditional novelty 4.0 of 10

    A post-training pipeline combining SFT, GRPO reinforcement learning, and corrective self-consistency lifts 0.5B-1.5B models to 56.9%-67.1% execution accuracy on BIRD dev.

  34. SQLord: A Robust Enterprise Text-to-SQL Solution via Reverse Data Generation and Workflow Decomposition

    cs.DB 2025-07 unverdicted novelty 4.0 of 10

    SQLord builds a domain-specific text-to-SQL pipeline using reverse-generated query-SQL training pairs, workflow decomposition, and an LLM-based judge, reporting consistent gains over GPT-4 and open-source baselines.

  35. Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task

    cs.AI 2025-06 conditional novelty 4.0 of 10

    Schema-R1 combines cold-start SFT on 200 CoT samples with GRPO rule-based RL, reporting table and column filter accuracy gains of 10 percentage points or more over a fine-tuned baseline on Spider-dev.

  36. Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities

    cs.CL 2025-05 conditional novelty 4.0 of 10

    A systematic review organizing LLM-based text-to-SQL methods into pre-processing, in-context learning, fine-tuning, and post-processing paradigms, with a catalog of datasets, metrics, challenges, and future directions.

  37. PSM-SQL: Progressive Schema Learning with Multi-granularity Semantics for Text-to-SQL

    cs.DB 2025-02 reject novelty 4.0 of 10

    PSM-SQL iteratively filters tables and columns for text-to-SQL, but its best reported numbers come from a two-module ablation, not from the full three-level multi-granularity method described in the paper.

  38. eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processing

    cs.IR 2025-06 conditional novelty 3.0 of 10

    eSapiens combines text-to-SQL and hybrid retrieval-augmented generation with citation verification, and its evaluation on RAGTruth shows better contextual relevance than a FAISS baseline across most LLMs, at the cost ...

  39. Auto prompt sql: a resource-efficient architecture for text-to-sql translation in constrained environments

    cs.CL 2025-06 reject novelty 3.0 of 10

    AP-SQL combines schema filtering, retrieval-augmented generation, and reasoning prompts, reporting small accuracy gains on the Spider text-to-SQL benchmark.

Pith tools